I
A
E
S
I
n
t
e
r
n
at
io
n
al
Jou
r
n
al
of
A
r
t
if
ic
ia
l
I
n
t
e
ll
ig
e
n
c
e
(
I
J
-
A
I
)
V
ol
. 13, No. 4, D
e
c
e
m
be
r
2024, pp.
3750
~
3760
I
S
S
N
:
2252
-
8938
,
D
O
I
:
10.11591/
ij
a
i.
v13.i4.pp
3750
-
3760
3750
Jou
r
n
al
h
om
e
page
:
ht
tp
:
//
ij
ai
.
ia
e
s
c
or
e
.c
om
A
p
p
l
i
c
at
i
on
of
c
l
ass
i
f
i
c
at
i
on
al
gor
i
t
h
m
s f
or
sm
i
s
h
i
n
g
d
e
t
e
c
t
i
on
on
m
ob
i
l
e
d
e
vi
c
e
s:
l
i
t
e
r
at
u
r
e
r
e
vi
e
w
D
yl
an
F
ar
e
d
h
C
al
e
r
o S
in
c
h
e
, M
ar
ía
A
c
u
ñ
a M
e
lé
n
d
e
z
, C
h
r
is
t
ia
n
O
val
le
D
e
pa
r
t
a
m
e
nt
o de
I
nge
ni
e
r
í
a
, F
a
c
ul
t
a
d de
I
nge
ni
e
r
í
a
, U
ni
ve
r
s
i
da
d
T
e
c
nol
ógi
c
a
d
e
l
P
e
r
ú, L
i
m
a
, P
e
r
ú
A
r
t
ic
le
I
n
f
o
A
B
S
T
R
A
C
T
A
r
ti
c
le
h
is
to
r
y
:
R
e
c
e
iv
e
d
J
a
n 9, 2024
R
e
vi
s
e
d
M
a
r
1, 2024
A
c
c
e
pt
e
d
M
a
r
21, 2024
Smishing
is
a
form
of
phishing
carried
out
via
mobile
devices
t
o
steal
confident
ial
informat
ion
from
victim
s.
The
number
of
smishing
attac
ks
has
increase
d
in
recent
years
due
to
the
large
number
of
users
acquirin
g
these
easy
-
to
-
use
and
functional
devices.
This
literature
review
objectiv
e
is
to
examine
the
techniqu
es
and
methods
used
in
smishing
attacks
using
classifi
cation
algorit
hms.
To
do
so,
we
conducted
a
manual
search
process
and select
ed 155 art
icles fro
m Scopu
s and 29
articles
from
access to
re
search
for
dev
elopment
and
innovat
ion
(
ARDI
)
.
Of
these,
36
articles
m
et
the
inclusion
criteria
.
In
addition,
the
algorithms
most
commonly
used
by
the
studies
were
random
for
est
classification
te
chniques,
decision
tr
ee
s,
and
neural
networks.
These
studies
analy
zed
various
machine
learning
models
for
detecting
phishing
and
smishing
messages.
The
attack
sim
ulation
scenarios
included
generating
web
pages,
sending
fake
links
(URL
s),
and
installing
malicious
applications
.
The
analysis
evaluate
d
web
pag
es
and
SMS
messages
using
a
database
containing
legitimate
as
well
as
s
mishing
messages.
Based
on
the
results,
it
is
suggested
to
combine
these
meth
ods
to
improve de
tection per
formance
, making it more
robust and
promising.
K
e
y
w
o
r
ds
:
A
r
ti
f
ic
ia
l
in
te
ll
ig
e
nc
e
M
a
c
hi
ne
le
a
r
ni
ng
M
obi
le
phi
s
hi
ng
M
obi
le
s
e
c
ur
it
y
S
m
is
hi
ng
This is an
open
acce
ss artic
le unde
r the
CC BY
-
SA
license.
C
or
r
e
s
pon
di
n
g A
u
th
or
:
C
hr
is
ti
a
n O
va
ll
e
D
e
pa
r
ta
m
e
nt
o de
I
nge
ni
e
r
ía
, F
a
c
ul
ta
d de
I
nge
ni
e
r
ía
, U
ni
ve
r
s
id
a
d T
e
c
nol
ógi
c
a
d
e
l
P
e
r
ú
A
v. P
e
ti
t
T
houa
r
s
116, L
im
a
15046, P
e
r
u
E
m
a
il
:
dova
ll
e
@
ut
p.e
du.pe
1.
I
N
T
R
O
D
U
C
T
I
O
N
C
ur
r
e
nt
ly
,
th
e
in
c
r
e
a
s
e
in
m
obi
le
c
onne
c
ti
vi
ty
ha
s
in
c
r
e
a
s
e
d
e
xpone
nt
ia
ll
y,
w
hi
c
h
ha
s
le
d
to
th
e
e
m
e
r
ge
nc
e
of
ne
w
us
e
r
s
w
ho,
th
r
ough
th
e
e
a
s
e
of
f
e
r
e
d
by
c
e
ll
phone
s
,
pe
r
f
or
m
va
r
io
us
pr
oc
e
s
s
e
s
w
it
h
th
e
m
[
1]
–
[
3]
,
th
e
m
a
in
one
s
a
r
e
r
e
s
e
a
r
c
hi
ng,
ba
nk
pa
ym
e
nt
s
,
s
hopping,
s
a
le
s
,
e
nt
e
r
ta
in
m
e
nt
,
a
nd
s
tu
dyi
ng.
I
n
tu
r
n,
th
e
in
c
r
e
a
s
e
d
us
e
of
c
e
ll
phone
s
ha
s
e
xpo
s
e
d
us
e
r
s
to
gr
ow
in
g
r
is
ks
s
uc
h
a
s
phi
s
hi
ng,
m
a
lwa
r
e
,
a
nd
s
m
is
hi
n
[
4]
, [
5]
, t
he
l
a
tt
e
r
be
in
g a
gr
ow
in
g p
r
obl
e
m
s
in
c
e
i
t
is
a
va
r
ia
nt
of
phi
s
hi
ng s
pe
c
if
ic
a
ll
y t
a
r
ge
te
d a
t
s
m
a
r
tp
hone
us
e
r
s
. T
he
r
e
f
or
e
,
th
is
ty
p
e
of
a
tt
a
c
k
r
e
pr
e
s
e
nt
s
a
s
ig
ni
f
ic
a
nt
th
r
e
a
t
due
to
th
e
in
c
r
e
a
s
e
in
th
e
num
be
r
of
pe
opl
e
w
ho
pe
r
f
or
m
tr
a
ns
a
c
ti
ons
[
6]
a
nd
ope
r
a
ti
ons
th
r
ough
th
e
ir
m
obi
le
de
vi
c
e
s
.
A
ddi
ti
ona
ll
y,
90%
of
us
e
r
s
ope
n
S
M
S
m
e
s
s
a
g
e
s
im
m
e
di
a
te
ly
upon
r
e
c
e
ip
t,
r
e
ga
r
dl
e
s
s
of
th
e
s
e
nde
r
[
7]
,
w
hi
c
h
in
c
r
e
a
s
e
s
th
e
li
ke
li
hood
of
in
f
or
m
a
ti
on t
he
f
t.
H
e
nc
e
,
th
i
s
li
te
r
a
t
ur
e
r
e
vi
e
w
a
im
s
to
e
xpl
or
e
th
e
c
ur
r
e
nt
s
t
a
te
of
kno
w
le
d
ge
in
de
v
e
lo
pi
ng
s
e
c
ur
it
y
m
ode
l
s
b
a
s
e
d
on
c
l
a
s
s
if
i
c
a
ti
o
n
a
lg
or
it
h
m
s
f
or
de
t
e
c
ti
n
g
s
m
i
s
hi
n
g
on
m
obi
le
de
v
ic
e
s
.
C
ons
e
qu
e
nt
ly
,
it
s
e
e
ks
to
pr
ovi
de
a
c
r
it
ic
a
l
f
ound
a
ti
on
f
or
th
e
c
ont
i
nuou
s
im
pr
ov
e
m
e
nt
of
m
obi
le
s
e
c
ur
it
y
a
n
d
pr
ot
e
c
ti
on
a
ga
in
s
t
s
m
is
hi
ng
th
r
e
a
t
s
.
I
n a
ddr
e
s
s
in
g
th
is
s
e
c
ur
it
y
i
s
s
ue
e
f
f
ic
ie
nt
ly
,
it
i
s
c
r
u
c
ia
l
t
o
c
on
s
id
e
r
th
e
pot
e
nt
ia
l
of
e
m
e
r
g
in
g
te
c
hn
ol
ogi
e
s
,
a
s
th
e
y
a
s
s
is
t
in
c
lo
s
in
g
pr
e
s
e
n
t
ga
p
s
[
8]
.
B
lo
c
kc
ha
i
n
te
c
hnol
og
y,
a
s
one
s
uc
h
a
dv
a
nc
e
m
e
nt
,
r
e
nde
r
s
da
t
a
im
m
u
ta
bl
e
[
9]
a
nd
ha
s
d
e
m
on
s
tr
a
t
e
d
pr
om
is
e
a
n
d
a
da
pt
a
bi
li
t
y
a
c
r
os
s
v
a
r
io
u
s
te
c
hnol
ogi
c
a
l
a
nd
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
A
r
ti
f
I
nt
e
ll
I
S
S
N
:
2252
-
8938
A
ppl
ic
at
io
n of
c
la
s
s
if
ic
at
io
n al
gor
it
hm
s
f
or
s
m
i
s
hi
ng de
te
c
ti
on
on m
obi
le
…
(
D
y
la
n F
ar
e
dh C
al
e
r
o Si
nc
he
)
3751
c
ybe
r
s
e
c
ur
it
y
f
i
e
ld
s
[
10]
–
[
14]
.
N
e
v
e
r
th
e
l
e
s
s
,
it
i
s
im
por
ta
nt
to
not
e
t
ha
t,
de
s
pi
t
e
it
s
p
ot
e
nt
ia
l
a
dv
a
nt
a
ge
s
,
t
he
pr
a
c
ti
c
a
l
im
pl
e
m
e
nt
a
ti
on
of
bl
oc
kc
h
a
in
t
e
c
hnol
og
y
f
a
c
e
s
c
h
a
ll
e
nge
s
r
e
q
ui
r
in
g
c
a
r
e
f
ul
a
tt
e
nt
io
n
in
pa
r
a
ll
e
l
[
15]
.
S
tu
di
e
s
in
c
yb
e
r
s
e
c
ur
it
y
ha
v
e
id
e
n
ti
f
ie
d
a
n
in
c
r
e
a
s
e
in
phi
s
hi
ng
a
tt
a
c
k
s
ta
r
g
e
ti
ng
e
nd
u
s
e
r
s
w
ho
ut
il
i
z
e
s
m
a
r
tp
hone
s
[
16]
.
F
ur
th
e
r
m
or
e
,
a
n
a
n
a
ly
s
is
of
th
e
d
e
c
e
nt
r
a
li
z
a
ti
on
of
s
e
r
vi
c
e
s
on
th
e
I
nt
e
r
n
e
t,
s
pe
c
if
ic
a
l
ly
r
e
ga
r
di
n
g
dom
a
in
n
a
m
e
s
y
s
te
m
(
D
N
S
)
,
w
a
s
c
o
ndu
c
te
d.
T
hi
s
a
na
ly
s
is
hi
ghl
ig
ht
s
bl
oc
kc
h
a
in
t
e
c
h
nol
ogy
a
s
a
n
e
s
s
e
nt
ia
l
to
ol
a
nd
de
lv
e
s
i
nt
o
th
e
th
r
e
a
ts
a
nd
r
i
s
k
s
a
s
s
oc
ia
te
d
w
it
h
D
N
S
d
e
c
e
nt
r
a
li
z
a
ti
o
n
[
17]
.
T
he
bl
oc
kc
h
a
in
is
us
e
d
to
e
nh
a
nc
e
s
e
c
ur
it
y
i
n
de
t
e
c
ti
ng
phi
s
hi
n
g
a
tt
a
c
k
s
i
n
th
e
c
lo
ud,
e
m
pha
s
i
z
in
g
th
e
im
por
t
a
nc
e
of
pr
ot
e
c
ti
ng
us
e
r
da
t
a
in
th
a
t
e
nvi
r
o
nm
e
nt
[
18]
.
C
on
s
id
e
r
in
g
bot
h
e
m
e
r
gi
n
g
a
nd
e
s
t
a
bl
i
s
he
d
t
e
c
h
nol
ogi
e
s
a
nd
a
ddr
e
s
s
in
g
th
e
la
c
k
of
c
om
pr
e
he
ns
i
ve
c
la
s
s
if
i
c
a
ti
ons
of
m
e
t
ho
dol
ogi
e
s
to
c
ou
nt
e
r
s
m
i
s
hi
ng
[
19]
,
th
i
s
r
e
vi
e
w
c
ove
r
s
br
o
a
d
a
nd u
pda
t
e
d
a
ppr
o
a
c
h
e
s
to
s
tr
e
ngt
he
n
s
e
c
ur
it
y on
m
obi
le
de
vi
c
e
s
a
ga
in
s
t
s
m
i
s
hi
ng
th
r
e
a
ts
.
I
n
th
i
s
c
ont
e
xt
,
th
e
r
e
s
e
a
r
c
h
a
im
s
t
o
i
de
nt
if
y
th
e
m
a
in
m
e
c
h
a
ni
s
m
s
a
nd
a
ppr
oa
c
he
s
to
de
t
e
c
t
phi
s
hi
ng
a
nd
s
m
i
s
hi
ng
a
tt
a
c
k
s
.
D
ue
to
th
e
in
c
r
e
a
s
e
in
th
e
s
e
ty
p
e
s
of
a
tt
a
c
ks
,
t
he
obj
e
c
ti
ve
i
s
to
a
n
a
ly
z
e
te
c
hni
q
ue
s
a
nd
m
e
th
od
s
b
a
s
e
d
on
c
la
s
s
if
ic
a
ti
on
a
lg
or
it
hm
s
to
e
nh
a
nc
e
our
un
de
r
s
t
a
ndi
n
g
of
t
he
pot
e
nt
ia
l
da
n
ge
r
s
po
s
e
d
by
s
uc
h
a
tt
a
c
ks
.
T
h
e
r
e
f
or
e
,
th
e
s
tu
d
y
i
s
s
tr
u
c
tu
r
e
d
a
s
f
ol
lo
w
s
:
th
e
m
e
th
odo
lo
gy
s
e
c
ti
on
de
s
c
r
ib
e
s
th
e
s
y
s
te
m
a
ti
c
li
te
r
a
tu
r
e
r
e
vi
e
w
m
e
th
o
d
e
m
pl
o
ye
d,
in
c
lu
di
ng
th
e
r
e
s
e
a
r
c
h
qu
e
s
ti
ons
a
nd
th
e
s
e
le
c
ti
on
pr
o
c
e
s
s
of
th
e
a
n
a
ly
z
e
d
m
a
te
r
ia
l.
F
ur
th
e
r
m
or
e
,
th
e
r
e
s
ul
t
s
s
e
c
t
io
n
pr
e
s
e
nt
s
a
nd
or
ga
ni
z
e
s
th
e
t
e
c
hni
qu
e
s
a
nd
m
e
th
od
s
a
ppl
ie
d,
ut
il
i
z
in
g
e
xi
s
t
in
g c
l
a
s
s
if
i
c
a
ti
o
n a
lg
or
it
hm
s
. S
im
il
a
r
l
y, t
h
e
di
s
c
u
s
s
i
on de
lv
e
s
i
nt
o t
he
c
ont
r
o
ve
r
s
y s
ur
r
o
undi
n
g t
he
s
our
c
e
s
a
nd
c
la
s
s
if
ic
a
ti
on
a
lg
or
it
hm
s
s
e
l
e
c
t
e
d,
pr
ovi
di
ng
in
te
r
pr
e
ta
ti
ve
c
r
it
e
r
ia
on
th
e
s
ta
t
e
of
th
e
a
r
t
,
c
ur
r
e
nt
pe
r
s
p
e
c
ti
ve
s
,
a
nd
li
m
it
a
ti
on
s
.
F
in
a
ll
y,
th
e
c
o
nc
lu
s
io
ns
s
e
c
ti
on
s
um
m
a
r
iz
e
s
t
he
m
a
in
r
e
s
ul
t
s
a
n
d
li
m
it
a
t
io
n
s
of
th
is
s
y
s
te
m
a
ti
c
l
it
e
r
a
tu
r
e
r
e
vi
e
w
s
tu
dy
a
nd
s
u
gge
s
t
s
di
r
e
c
ti
on
s
f
o
r
f
ut
ur
e
r
e
s
e
a
r
c
h
on t
h
e
s
ubj
e
c
t.
2.
M
E
T
H
O
D
O
L
O
G
Y
T
he
r
e
vi
e
w
m
e
th
odol
ogy
e
m
pl
oye
d
a
dhe
r
e
s
to
th
e
popula
ti
on,
in
te
r
ve
nt
io
n,
c
ont
r
ol
,
a
nd
out
c
om
e
s
(
P
I
C
O
)
c
r
it
e
r
ia
f
or
th
e
f
or
m
ul
a
ti
on
of
r
e
s
e
a
r
c
h
que
s
ti
ons
.
A
c
c
or
di
ngl
y,
a
s
e
r
ie
s
of
s
te
ps
w
e
r
e
f
ol
lo
w
e
d
th
a
t
c
ove
r
e
d
th
e
f
or
m
ul
a
ti
on
o
f
que
s
ti
ons
,
th
e
s
e
le
c
ti
on
of
ke
yw
or
ds
,
th
e
s
c
ope
of
th
e
r
e
vi
e
w
,
th
e
de
f
in
i
ti
on
o
f
in
c
lu
s
io
n
a
nd
e
xc
lu
s
io
n
c
r
it
e
r
ia
,
a
nd
th
e
e
xe
c
ut
io
n
of
th
e
s
e
a
r
c
h
s
e
que
nc
e
.
T
hu
s
,
th
e
s
e
le
c
ti
on
of
in
f
or
m
a
ti
on
a
r
ti
c
le
s
w
a
s
pe
r
f
or
m
e
d
a
c
c
or
di
ng
to
th
e
pr
e
f
e
r
r
e
d
r
e
por
t
in
g
it
e
m
s
f
or
s
ys
te
m
a
ti
c
r
e
vi
e
w
s
a
nd
m
e
ta
-
a
na
ly
s
e
s
(
P
R
I
S
M
A
)
gui
de
li
ne
s
,
w
hi
c
h
he
lp
in
w
r
it
in
g
a
nd
be
tt
e
r
r
e
c
ogni
z
in
g
th
e
ke
y
a
s
pe
c
ts
to
be
c
ons
id
e
r
e
d
[
20]
,
[
21]
.
D
a
ta
e
xt
r
a
c
ti
on
w
a
s
pe
r
f
or
m
e
d
us
in
g
a
f
or
m
a
da
pt
e
d
to
c
om
pa
r
e
th
e
in
f
or
m
a
ti
on
e
xt
r
a
c
te
d
f
r
o
m
th
e
a
r
ti
c
le
s
s
tu
di
e
d.
A
to
ta
l
of
36
a
r
ti
c
le
s
w
e
r
e
a
na
ly
z
e
d
to
s
tr
e
ng
th
e
n
th
e
ba
s
is
of
th
e
r
e
vi
e
w
.
S
ubs
e
que
nt
ly
,
a
c
om
pr
e
he
ns
iv
e
a
na
ly
s
is
of
t
he
r
e
s
ul
ts
obt
a
in
e
d w
a
s
c
a
r
r
ie
d out, f
ol
lo
w
e
d by the
pr
e
s
e
nt
a
ti
on of
t
he
di
s
c
us
s
io
n
of
th
e
r
e
s
ul
ts
a
nd
th
e
f
or
m
ul
a
ti
on
of
c
onc
lu
s
iv
e
c
onc
lu
s
io
ns
of
th
e
s
tu
dy.
U
s
in
g
P
R
I
S
M
A
,
th
e
m
os
t
r
e
le
va
nt
a
r
ti
c
le
s
c
lo
s
e
ly
a
li
gne
d
w
it
h
our
r
e
s
e
a
r
c
h
to
pi
c
w
e
r
e
s
ys
te
m
a
ti
c
a
ll
y
s
e
le
c
te
d.
A
s
te
pw
is
e
s
e
le
c
ti
on
pr
oc
e
s
s
w
a
s
de
v
e
lo
pe
d,
gui
de
d
by
th
e
pr
in
c
ip
le
s
de
s
c
r
ib
e
d
in
th
e
P
R
I
S
M
A
s
ta
t
e
m
e
nt
[
20]
,
to
a
c
hi
e
v
e
de
ta
il
e
d
c
r
it
e
r
ia
a
nd
f
il
te
r
s
a
ppl
ie
d
in
th
e
li
te
r
a
tu
r
e
on
th
e
to
pi
c
of
our
r
e
vi
e
w
,
s
pe
c
if
ic
a
ll
y,
th
e
a
ppl
ic
a
ti
on
of
c
la
s
s
if
ic
a
ti
on
a
lg
or
it
hm
s
f
or
t
he
de
te
c
ti
on of
i
m
pe
r
s
ona
ti
on on mobi
le
de
vi
c
e
s
.
A
to
ta
l
of
f
our
r
e
s
e
a
r
c
h
que
s
ti
ons
(
R
Q
)
w
e
r
e
f
or
m
ul
a
te
d
f
ol
lo
w
in
g
th
e
P
I
C
O
f
r
a
m
e
w
or
k
to
c
onduc
t
a
c
om
pr
e
he
ns
iv
e
r
e
vi
e
w
of
th
e
to
pi
c
[
22]
.
I
n
th
is
s
tu
dy,
th
e
p
opul
a
ti
on
(
P
)
is
c
om
pos
e
d
of
s
m
is
hi
ng
a
nd
it
s
de
r
iv
a
ti
ve
s
,
th
e
in
te
r
ve
nt
io
n
(
I
)
c
ons
id
e
r
e
d
in
vol
ve
s
th
e
a
pp
li
c
a
ti
on
of
c
la
s
s
if
ic
a
ti
on
a
lg
or
it
hm
s
,
a
nd
th
e
out
c
om
e
s
(
O
)
r
e
f
e
r
t
o t
he
f
i
r
s
t
r
e
s
ul
ts
obt
a
in
e
d. C
ons
e
que
nt
ly
,
w
e
f
or
m
ul
a
te
d f
our
R
Q
s
t
ha
t
gui
de
t
he
pur
pos
e
of
th
e
s
tu
dy,
a
s
de
ta
il
e
d
in
T
a
bl
e
1.
C
ont
e
xt
(
C
)
f
oc
us
e
s
on
m
obi
le
de
vi
c
e
s
.
U
lt
im
a
te
ly
,
th
e
P
I
C
O
que
s
ti
on
is
f
or
m
ul
a
te
d
a
s
f
ol
lo
w
s
,
w
ha
t
is
th
e
opt
im
a
l
a
ppr
oa
c
h
to
de
ve
lo
pi
ng
a
s
e
c
ur
it
y
m
ode
l
th
a
t
us
e
s
c
l
a
s
s
if
ic
a
ti
on
a
lg
or
it
hm
s
f
or
s
m
is
hi
ng
de
te
c
ti
on?
T
a
bl
e
1. R
e
s
e
a
r
c
h qu
e
s
ti
ons
a
n
s
w
e
r
in
g t
he
P
I
C
O
que
s
ti
on
Re
s
e
a
rc
h
que
s
t
i
ons
Re
s
ul
t
RQ
1.
W
ha
t
a
re
t
he
s
pe
c
i
fi
c
va
ri
a
nt
s
of
m
obi
l
e
phi
s
hi
ng
t
ha
t
ha
ve
be
e
n
us
e
d
a
s
t
he
obj
e
c
t
of
s
t
udy?
−
D
e
s
c
ri
pt
i
on
of
t
he
probl
e
m
.
−
O
bj
e
c
t
i
v
e
of
t
he
re
s
e
a
rc
h.
RQ
2.
W
ha
t
w
e
re
t
he
s
ol
ut
i
ons
i
m
pl
e
m
e
nt
e
d
t
hrough
t
he
c
l
a
s
s
i
fi
c
a
t
i
on
a
l
gor
i
t
hm
s
for
s
m
i
s
hi
ng
de
t
e
c
t
i
on?
−
W
ha
t
m
ode
l
s
w
e
re
us
e
d
i
n
t
he
de
ve
l
opm
e
nt
of
t
he
s
t
udy.
−
D
e
s
c
ri
pt
i
on
of
t
he
a
l
gori
t
h
m
i
m
pl
e
m
e
n
t
e
d.
RQ
3.
W
ha
t
w
e
re
t
he
re
s
ul
t
s
obt
a
i
ne
d
by
a
ppl
yi
ng
t
he
propos
e
d
s
ol
ut
i
ons
?
−
E
va
l
ua
t
i
on
m
e
t
r
i
c
s
a
ppl
i
e
d.
−
A
c
hi
e
ve
m
e
nt
s
a
t
t
a
i
ne
d.
−
L
i
m
i
t
a
t
i
ons
of
t
he
c
a
s
e
s
t
udy.
RQ
4.
W
ha
t
pra
c
t
i
c
e
s
a
re
re
c
om
m
e
nde
d
for
s
m
i
s
hi
ng
de
t
e
c
t
i
on
a
nd
m
i
t
i
ga
t
i
on?
−
Re
c
om
m
e
nda
t
i
ons
pre
s
e
nt
e
d
by
t
he
a
ut
hors
.
2.1. Ke
yw
or
d
s
e
le
c
t
io
n
K
e
yw
or
ds
w
e
r
e
s
e
le
c
te
d
a
c
c
or
di
ng
to
th
e
s
tu
dy
a
ppr
oa
c
h
f
or
t
he
e
xt
r
a
c
ti
on
of
in
f
or
m
a
ti
on
s
our
c
e
s
.
T
he
s
e
te
r
m
s
,
c
om
pos
e
d
of
one
or
m
or
e
w
o
r
ds
,
s
e
r
ve
a
s
de
s
c
r
ip
to
r
s
f
or
th
e
c
a
s
e
s
tu
dy
que
r
ie
s
,
gui
di
ng
th
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8938
I
nt
J
A
r
ti
f
I
nt
e
ll
, V
ol
. 13, No. 4, D
e
c
e
m
be
r
2024:
3750
-
3760
3752
s
e
a
r
c
h
e
ngi
ne
que
r
ie
s
to
obt
a
in
r
e
le
va
nt
a
ns
w
e
r
s
a
nd
s
ol
ve
th
e
r
e
s
e
a
r
c
h
pr
obl
e
m
s
pos
e
d. T
a
bl
e
2
pr
e
s
e
nt
s
th
e
s
pe
c
if
ic
ke
yw
or
ds
u
s
e
d.
I
n
a
ddi
ti
on,
th
e
S
c
opus
a
nd
a
c
c
e
s
s
to
r
e
s
e
a
r
c
h
f
or
de
ve
lo
pm
e
nt
a
nd
in
nova
ti
on
(
A
R
D
I)
da
ta
ba
s
e
s
w
e
r
e
us
e
d t
o pe
r
f
or
m
a
s
e
m
a
nt
ic
s
e
a
r
c
h of
t
h
e
que
s
ti
ons
po
s
e
d i
n t
he
P
I
C
O
m
e
th
odol
ogy.
T
a
bl
e
2. K
e
yw
or
d
s
-
s
e
a
r
c
h s
ynt
a
x
I
t
e
m
K
e
yw
or
ds
S
e
a
r
c
h e
qua
t
i
on s
ynt
a
x
P
M
obi
l
e
phi
s
hi
ng,
s
m
i
s
hi
ng
P
hi
s
hi
ng O
R
s
uppl
a
nt
a
t
i
on O
R
“
P
hi
s
hi
ng c
r
i
m
e
”
O
R
s
m
i
s
hi
ng
I
M
a
c
hi
ne
l
e
a
r
ni
ng, a
r
t
i
f
i
c
i
a
l
i
nt
e
l
l
i
ge
nc
e
,
de
e
p
l
e
a
r
ni
ng,
s
uppor
t
ve
c
t
or
m
a
c
hi
ne
(
S
V
M
)
,
r
a
ndom
f
or
e
s
t
t
r
e
e
s
(
R
F
T
)
.
“
A
r
t
i
f
i
c
i
a
l
i
nt
e
l
l
i
ge
nc
e
”
O
R
“
M
a
c
hi
n
e
l
e
a
r
ni
ng”
O
R
“
D
e
e
p l
e
a
r
ni
ng”
O
R
“
A
r
t
i
f
i
c
i
a
l
ne
ur
a
l
ne
t
w
or
ks
”
O
R
“
S
uppor
t
ve
c
t
or
m
a
c
hi
ne
s
”
O
R
“
D
e
c
i
s
i
on
t
r
e
e
s
”
O
R
“
R
a
ndom
F
or
e
s
t
t
e
c
hni
que
”
O
D
e
t
e
c
t
i
on,
m
i
t
i
ga
t
i
on, vul
ne
r
a
bi
l
i
t
i
e
s
,
i
nf
or
m
a
t
i
on l
e
a
ka
ge
, m
obi
l
e
s
e
c
ur
i
t
y
D
e
t
e
c
t
i
on O
R
m
i
t
i
ga
t
i
on O
R
a
ut
he
nt
i
c
a
t
i
on O
R
"P
hi
s
hi
ng de
t
e
c
t
i
on" O
R
V
ul
ne
r
a
bi
l
i
t
i
e
s
O
R
“
M
obi
l
e
s
e
c
ur
i
t
y”
O
R
“
I
nf
or
m
a
t
i
on L
e
a
k”
O
R
P
hi
s
hi
ng
a
t
t
a
c
ks
O
R
L
os
s
e
s
O
R
T
hr
e
a
t
s
C
M
obi
l
e
P
hone
s
/
S
m
a
r
t
phone
"M
obi
l
e
de
vi
c
e
s
" O
R
S
m
a
r
t
phone
O
R
M
obi
l
e
O
R
“
S
m
a
r
t
de
vi
c
e
s
”
O
R
A
ndr
oi
d
2.2. S
e
ar
c
h
s
e
q
u
e
n
c
e
T
he
s
e
a
r
c
h
f
or
in
f
or
m
a
ti
on
s
our
c
e
s
w
a
s
c
a
r
r
ie
d
out
in
th
e
S
c
opus
a
nd
A
R
D
Í
da
t
a
ba
s
e
s
.
T
he
s
c
ie
nt
if
ic
s
tu
di
e
s
to
be
c
ons
id
e
r
e
d
c
ove
r
th
e
pe
r
io
d
f
r
om
201
8
to
2023.
T
he
a
lg
or
it
hm
obt
a
in
e
d
f
r
om
th
is
s
e
que
nc
e
w
a
s
a
ppl
ie
d t
o t
he
t
it
le
,
a
bs
tr
a
c
t,
a
nd ke
y
w
or
ds
t
o a
ns
w
e
r
t
he
P
I
C
O
r
e
vi
e
w
que
s
ti
on.
2.3. S
e
ar
c
h
al
gor
it
h
m
A
s
e
a
r
c
h
a
lg
or
it
hm
w
a
s
e
xe
c
ut
e
d
on
th
e
S
c
opus
a
nd
A
R
D
Í
da
ta
ba
s
e
s
,
yi
e
ld
in
g
184
in
f
or
m
a
ti
on
s
our
c
e
s
. A
ut
om
a
ti
c
f
il
te
r
s
w
e
r
e
a
ppl
ie
d t
o s
e
le
c
t
doc
um
e
nt
s
r
e
le
va
nt
t
o t
he
pr
opos
e
d r
e
vi
e
w
t
opi
c
, a
s
out
li
ne
d
in
T
a
bl
e
3.
T
he
pr
opos
e
d
a
lg
or
it
hm
w
a
s
de
s
ig
ne
d
m
e
ti
c
ul
ous
ly
to
a
li
gn
w
it
h
th
e
P
I
C
O
r
e
vi
e
w
que
s
ti
on
to
e
nha
nc
e
m
obi
le
phi
s
hi
ng
de
te
c
ti
on
c
a
pa
bi
li
ti
e
s
.
B
y
e
m
pl
oyi
ng
s
ys
te
m
a
ti
c
f
il
te
r
s
a
nd
c
r
it
e
r
ia
,
th
e
pr
opos
e
d
a
lg
or
it
hm
i
de
nt
if
ie
d pe
r
ti
ne
nt
s
tu
di
e
s
a
nd da
ta
s
e
t
s
e
s
s
e
nt
ia
l
f
or
r
ig
or
ous
a
na
ly
s
is
i
n t
hi
s
s
p
e
c
ia
li
z
e
d f
ie
ld
.
T
a
bl
e
3. S
e
a
r
c
h a
lg
or
it
hm
s
D
a
t
a
ba
s
e
S
e
a
r
c
h a
l
gor
i
t
hm
s
S
C
O
P
U
S
T
I
T
L
E
-
A
B
S
-
K
E
Y
(
phi
s
hi
ng O
R
"P
hi
s
hi
ng M
obi
l
e
" O
R
s
uppl
a
nt
a
t
i
on O
R
"P
hi
s
hi
ng c
r
i
m
e
" O
R
s
m
i
s
hi
ng
)
A
N
D
T
I
T
L
E
-
A
B
S
-
K
E
Y
(
"ma
c
hi
ne
l
e
a
r
ni
ng" O
R
"D
e
c
i
s
i
on T
r
e
e
" O
R
"D
e
e
p l
e
a
r
ni
n
g" O
R
"ne
ur
a
l
ne
t
w
or
k" O
R
"S
uppor
t
ve
c
t
or
m
a
c
hi
ne
s
" O
R
c
onvol
ut
i
ona
l
O
R
"B
a
y
e
s
i
a
n ne
t
w
or
k" O
R
"R
a
ndom
F
or
e
s
t
t
e
c
hni
que
" )
A
N
D
T
I
T
L
E
-
A
B
S
-
K
E
Y
(
de
t
e
c
t
i
on O
R
m
i
t
i
ga
t
i
on O
R
a
ut
he
nt
i
c
a
t
i
on O
R
vul
ne
r
a
bi
l
i
t
i
e
s
O
R
"M
obi
l
e
s
e
c
ur
i
t
y" O
R
"I
nf
or
m
a
t
i
on L
e
a
k" O
R
l
os
s
e
s
O
R
t
hr
e
a
t
s
)
A
N
D
T
I
T
L
E
-
A
B
S
-
K
E
Y
(
“
M
obi
l
e
de
vi
c
e
s
" O
R
s
m
a
r
t
phone
O
R
m
obi
l
e
O
R
"S
m
a
r
t
de
vi
c
e
s
" O
R
a
ndr
oi
d)
.
A
R
D
I
P
hi
s
hi
ng A
N
D
m
obi
l
e
A
N
D
“
m
a
c
hi
ne
l
e
a
r
ni
ng”
A
N
D
s
e
c
ur
i
t
y
2.4. De
f
in
it
io
n
of
i
n
c
lu
s
io
n
an
d
e
xc
lu
s
io
n
c
r
it
e
r
ia
T
he
f
ol
lo
w
in
g r
e
vi
e
w
s
tu
dy de
te
r
m
in
e
s
t
he
poi
nt
s
t
o
be
de
ve
lo
pe
d ba
s
e
d on the
qua
li
ty
a
nd upda
ti
ng
of
th
e
in
f
or
m
a
ti
on.
I
n
de
f
in
in
g
th
e
pr
opos
e
d
c
r
it
e
r
ia
f
or
th
e
a
r
t
ic
le
s
,
w
e
c
ons
id
e
r
e
d
s
tu
di
e
s
th
a
t
pr
e
s
e
nt
c
le
a
r
in
f
or
m
a
ti
on
on
th
e
m
e
th
odol
ogy
a
ppl
ie
d
to
th
e
c
a
s
e
s
tu
dy,
th
e
ye
a
r
of
publ
ic
a
ti
on,
th
e
la
ngua
ge
,
a
nd
th
e
ty
p
e
of
doc
um
e
nt
. T
he
f
ol
lo
w
in
g i
nc
lu
s
io
n a
nd e
xc
lu
s
io
n c
r
it
e
r
ia
w
e
r
e
us
e
d, a
s
s
how
n i
n T
a
bl
e
s
4 a
nd 5.
T
a
bl
e
4. I
nc
lu
s
io
n c
r
it
e
r
ia
C
r
i
t
e
r
i
a
J
us
t
i
f
i
c
a
t
i
on
R
e
s
e
a
r
c
h f
oc
u
s
S
t
udi
e
s
s
houl
d
a
ddr
e
s
s
t
he
m
a
ni
f
e
s
t
a
t
i
on of
P
hi
s
hi
ng on m
obi
l
e
de
vi
c
e
s
.
I
m
por
t
a
nc
e
f
a
c
t
or
C
ont
a
i
n m
e
t
hods
or
t
e
c
hni
que
s
l
i
nke
d t
o c
l
a
s
s
i
f
i
c
a
t
i
on a
nd a
ppl
i
e
d t
o A
r
t
i
f
i
c
i
a
l
I
nt
e
l
l
i
ge
nc
e
.
E
xpe
r
i
m
e
nt
a
l
A
na
l
ys
e
s
a
ppl
i
e
d i
n r
e
a
l
e
nvi
r
onm
e
nt
s
, s
i
m
ul
a
t
i
on or
t
e
s
t
i
ng of
phi
s
hi
ng c
a
s
e
s
.
Q
ua
nt
i
t
a
t
i
ve
i
nf
or
m
a
t
i
on
R
e
s
e
a
r
c
h
s
houl
d r
e
por
t
s
t
a
t
i
s
t
i
c
a
l
r
e
s
ul
t
s
of
t
he
a
ppl
i
c
a
t
i
on of
s
uc
h m
e
t
hods
. of
t
he
a
ppl
i
c
a
t
i
on of
s
uc
h
m
e
t
hods
.
T
a
bl
e
5. E
xc
lu
s
io
n c
r
it
e
r
ia
C
r
i
t
e
r
i
a
J
us
t
i
f
i
c
a
t
i
on
T
ype
of
publ
i
c
a
t
i
on
T
he
s
i
s
, B
ooks
,
uni
ve
r
s
i
t
y book c
ha
pt
e
r
s
(
not
upda
t
e
d)
, c
onf
e
r
e
nc
e
pa
pe
r
.
I
m
por
t
a
nc
e
f
a
c
t
or
R
e
s
e
a
r
c
h t
ha
t
doe
s
not
c
l
e
a
r
l
y pr
e
s
e
nt
a
d
e
ve
l
opm
e
nt
m
e
t
hodol
ogy.
U
ni
t
of
a
na
l
ys
i
s
J
obs
t
ha
t
do not
c
ons
i
de
r
M
obi
l
e
P
hi
s
hi
ng,
s
m
i
s
hi
ng
a
s
t
he
i
r
f
oc
us
of
i
nt
e
r
e
s
t
.
T
ype
of
l
a
ngua
ge
L
a
ngua
ge
s
ot
he
r
t
ha
n E
ngl
i
s
h a
nd S
pa
ni
s
h.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
A
r
ti
f
I
nt
e
ll
I
S
S
N
:
2252
-
8938
A
ppl
ic
at
io
n of
c
la
s
s
if
ic
at
io
n al
gor
it
hm
s
f
or
s
m
i
s
hi
ng de
te
c
ti
on
on m
obi
le
…
(
D
y
la
n F
ar
e
dh C
al
e
r
o Si
nc
he
)
3753
F
ig
ur
e
1 s
how
s
t
he
P
R
I
S
M
A
f
lo
w
c
ha
r
t,
w
hi
c
h s
how
s
t
he
a
r
ti
c
l
e
s
e
le
c
ti
on pr
oc
e
s
s
f
or
de
ve
lo
pi
ng t
he
s
ys
te
m
a
ti
c
li
te
r
a
tu
r
e
r
e
vi
e
w
on
th
e
a
ppl
ic
a
ti
on
of
c
la
s
s
if
ic
a
ti
on
a
lg
or
it
hm
s
f
or
de
te
c
ti
ng
s
m
i
s
hi
ng
on
m
obi
le
de
vi
c
e
s
.
36
s
c
i
e
nt
if
ic
s
tu
di
e
s
w
e
r
e
obt
a
in
e
d
f
ol
lo
w
in
g
th
e
P
R
I
S
M
A
m
e
th
odol
ogy
to
a
ddr
e
s
s
th
e
r
e
s
e
a
r
c
h
que
s
ti
ons
pos
e
d. T
hu
s
, t
he
s
tu
di
e
s
w
e
r
e
c
la
s
s
if
ie
d a
c
c
or
di
ng t
o t
he
pr
obl
e
m
a
ddr
e
s
s
e
d by e
a
c
h a
ut
hor
t
hr
oug
h
a
f
ul
l
-
te
xt
r
e
vi
e
w
of
t
he
a
bs
tr
a
c
ts
, i
nt
r
oduc
ti
on, obje
c
ti
ve
s
, a
nd me
th
odol
ogy f
or
c
ol
le
c
ti
ng a
nd c
om
pa
r
in
g t
he
m
e
th
ods
a
ppl
ie
d a
c
c
or
di
ng t
o t
he
c
la
s
s
if
ic
a
ti
on a
lg
or
it
hm
s
us
e
d
f
or
s
m
is
hi
ng
de
te
c
ti
on.
F
ig
ur
e
1. P
R
I
S
M
A
f
lo
w
di
a
gr
a
m
3.
R
E
S
U
L
T
S
A
N
D
D
I
S
C
U
S
S
I
O
N
A
c
c
or
di
ng
to
th
e
r
e
s
ul
ts
obt
a
in
e
d
th
r
ough
th
e
P
R
I
S
M
A
m
e
th
odol
ogy
[
20]
,
in
f
or
m
a
ti
on
e
xt
r
a
c
ti
o
n
f
r
om
th
e
s
e
le
c
te
d
a
r
ti
c
le
s
w
a
s
c
a
r
r
ie
d
out
.
T
he
m
a
jo
r
it
y
of
t
he
s
tu
di
e
s
f
oc
us
e
d
on
tr
a
in
in
g
c
la
s
s
if
ic
a
ti
on
a
lg
or
it
hm
s
a
ppl
ie
d
in
va
r
io
us
c
a
s
e
s
[
23]
.
A
n
e
xh
a
us
ti
ve
a
na
ly
s
is
of
th
e
s
tu
di
e
s
w
a
s
c
onduc
te
d
to
id
e
nt
if
y
th
e
di
f
f
e
r
e
nt
m
e
th
ods
of
s
m
is
hi
ng
a
nd
phi
s
hi
ng
a
tt
a
c
ks
ta
r
ge
ti
ng
m
obi
le
de
vi
c
e
s
.
T
he
c
la
s
s
if
ic
a
ti
on
a
lg
or
it
hm
s
m
os
t
f
r
e
que
nt
ly
us
e
d
in
th
e
a
r
ti
c
le
s
w
e
r
e
r
a
ndom
f
or
e
s
t
c
la
s
s
if
ic
a
ti
on,
de
c
is
io
n
tr
e
e
s
,
lo
gi
s
ti
c
r
e
gr
e
s
s
io
n,
n
a
iv
e
B
a
ye
s
,
k
-
ne
a
r
e
s
t
ne
ig
hbor
s
,
a
nd
ne
ur
a
l
ne
twor
ks
.
T
he
s
e
a
lg
or
it
hm
s
w
e
r
e
th
e
m
os
t
im
pl
e
m
e
nt
e
d
in
th
e
s
e
le
c
te
d
s
tu
di
e
s
.
T
he
s
tu
di
e
s
de
m
ons
tr
a
te
th
a
t
s
m
i
s
hi
ng
is
c
ont
in
uous
ly
upda
te
d
a
s
ne
w
th
r
e
a
t
s
a
r
e
de
te
c
t
e
d,
a
nd
pos
it
iv
e
r
e
s
ul
ts
w
e
r
e
obt
a
in
e
d
us
in
g
th
e
c
la
s
s
if
ic
a
ti
on
a
lg
or
it
hm
s
m
e
nt
io
ne
d
in
th
is
r
e
vi
e
w
.
I
t
is
w
or
t
h
not
in
g
th
a
t
s
om
e
of
th
e
a
na
ly
z
e
d
s
our
c
e
s
di
d
not
pr
e
s
e
nt
e
xpe
r
im
e
nt
a
ti
on
of
th
e
ir
pr
opos
e
d
m
e
th
ods
.
I
ns
ta
nc
e
s
of
a
tt
a
c
k
s
im
ul
a
ti
on
in
vol
ve
d
a
c
c
e
s
s
in
g
w
e
bs
it
e
s
,
s
e
ndi
ng
f
a
ls
e
li
nks
(
U
R
L
s
)
,
in
s
ta
ll
in
g
m
a
li
c
io
us
a
ppl
ic
a
ti
ons
,
a
nd
im
pe
r
s
on
a
ti
ng
th
r
ough
S
M
S
m
e
s
s
a
g
e
s
.
T
he
e
va
lu
a
ti
on
of
w
e
b
pa
ge
s
a
nd
S
M
S
m
e
s
s
a
ge
s
w
a
s
c
onduc
t
e
d
us
in
g
a
da
ta
ba
s
e
of
le
gi
ti
m
a
te
a
nd
s
m
is
hi
ng
m
e
s
s
a
ge
s
.
T
he
f
ol
lo
w
in
g
s
e
c
ti
on
pr
e
s
e
nt
s
th
e
pr
oc
e
s
s
a
nd d
e
ve
lo
pm
e
nt
t
o a
ddr
e
s
s
t
he
r
e
vi
e
w
que
s
ti
on.
3.1.
B
ib
li
om
e
t
r
ic
d
at
a an
al
ys
is
I
n
th
is
s
e
c
ti
on,
c
on
s
id
e
r
a
ti
ons
r
e
la
te
d
to
th
e
s
tu
dy'
s
na
tu
r
e
a
n
d
th
e
publ
ic
a
ti
on
y
e
a
r
of
th
e
s
e
l
e
c
te
d
doc
um
e
nt
s
w
e
r
e
ta
ke
n
in
to
a
c
c
ount
to
ga
th
e
r
c
om
pr
e
he
ns
iv
e
i
ns
ig
ht
s
in
to
e
a
c
h
r
e
c
or
d.
C
ur
r
e
nt
ly
,
s
y
s
te
m
a
ti
c
r
e
vi
e
w
s
tu
di
e
s
f
oc
us
in
g
on
th
e
a
ddr
e
s
s
e
d
to
pi
c
a
r
e
s
c
a
r
c
e
.
C
o
ns
e
que
nt
ly
,
th
e
in
f
or
m
a
ti
on
c
ol
le
c
ti
on
pr
oc
e
s
s
r
e
li
e
d
on
a
r
ti
c
le
s
a
nd
c
onf
e
r
e
nc
e
pa
pe
r
s
to
s
ynt
he
s
iz
e
th
e
r
e
s
ul
ts
a
ppl
ie
d
in
e
a
c
h
s
tu
dy.
B
a
s
e
d
on
th
e
r
e
vi
e
w
r
e
s
ul
ts
,
th
e
a
na
ly
s
i
s
r
e
ve
a
le
d
th
a
t
24
pa
p
e
r
s
f
a
ll
und
e
r
th
e
c
a
te
gor
y
of
a
r
ti
c
le
s
,
w
hi
le
12
s
tu
di
e
s
a
r
e
c
la
s
s
if
ie
d
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8938
I
nt
J
A
r
ti
f
I
nt
e
ll
, V
ol
. 13, No. 4, D
e
c
e
m
be
r
2024:
3750
-
3760
3754
a
s
c
onf
e
r
e
nc
e
pa
pe
r
s
.
F
ig
ur
e
2
il
lu
s
tr
a
te
s
th
e
r
e
vi
e
w
e
d
a
r
ti
c
le
s
publ
is
h
e
d
f
r
om
2018
to
th
e
pr
e
s
e
nt
.
A
m
a
jo
r
it
y,
c
om
pr
is
in
g
70%
,
w
e
r
e
di
s
s
e
m
in
a
te
d
th
r
ough
a
r
ti
c
le
s
,
w
it
h
th
e
r
e
m
a
in
in
g
30%
pr
e
s
e
nt
e
d
in
c
onf
e
r
e
nc
e
pa
pe
r
s
.
T
h
e
a
r
ti
c
le
s
s
e
l
e
c
te
d
to
a
ns
w
e
r
th
e
r
e
vi
e
w
que
s
ti
on
s
how
a
n
in
c
r
e
a
s
e
f
r
om
th
e
ye
a
r
2022
in
th
e
c
onf
e
r
e
nc
e
pa
pe
r
s
a
nd
do
not
ha
ve
a
not
ic
e
a
bl
e
va
r
ia
ti
on
a
c
c
or
di
ng
to
th
e
publ
ic
a
ti
ons
m
a
de
in
th
e
c
our
s
e
of
t
he
ye
a
r
s
e
le
c
te
d a
s
i
n
c
lu
s
io
n c
r
it
e
r
ia
f
or
t
he
s
tu
di
e
s
.
F
ig
ur
e
2. P
ubl
ic
a
ti
ons
by ye
a
r
a
nd t
ype
of
s
tu
dy
3.2.
C
on
t
e
n
t
an
al
ys
is
T
hi
s
s
e
c
ti
on
w
il
l
s
ys
te
m
a
ti
c
a
ll
y
or
ga
ni
z
e
th
e
c
ol
le
c
te
d
in
f
or
m
a
ti
on
to
a
ddr
e
s
s
e
a
c
h
r
e
vi
e
w
que
s
ti
on
out
li
ne
d
in
th
e
m
e
th
odol
ogy.
I
t
w
il
l
a
ls
o
de
li
ne
a
te
th
e
c
r
it
ic
a
l
f
a
c
to
r
s
in
f
lu
e
nc
in
g
th
e
s
e
le
c
ti
on
of
te
c
hni
que
s
a
nd
a
lg
or
it
hm
s
e
m
pl
oye
d
a
c
r
os
s
th
e
s
tu
di
e
s
.
T
h
e
s
ub
s
e
que
nt
pr
e
s
e
nt
a
ti
on
w
il
l
unve
il
th
e
out
c
om
e
s
d
e
r
iv
e
d
f
r
om
t
he
s
ys
te
m
a
ti
c
a
na
ly
s
i
s
, pr
ovi
di
ng e
xpl
ic
it
r
e
s
pons
e
s
t
o t
he
r
e
vi
e
w
i
nqui
r
ie
s
.
‒
W
ha
t
is
th
e
opt
im
a
l
a
ppr
oa
c
h
f
or
c
r
a
f
ti
ng
a
s
e
c
ur
it
y
m
ode
l
u
ti
li
z
in
g
c
la
s
s
if
ic
a
ti
on
a
lg
or
it
hm
s
to
de
te
c
t
s
m
is
hi
ng
?
B
a
s
e
d
on
th
e
e
x
a
m
in
a
ti
on
of
th
e
s
c
r
ut
in
iz
e
d
s
tu
di
e
s
[
24]
–
[
28]
,
th
is
pa
pe
r
de
li
ne
a
te
s
a
n
opt
im
a
l
a
ppr
oa
c
h
f
or
c
r
a
f
ti
ng
a
nd
im
pl
e
m
e
nt
in
g
a
s
e
c
ur
it
y
m
ode
l
th
a
t
e
nc
om
pa
s
s
e
s
th
e
f
il
te
r
in
g
a
nd
de
ni
a
l
of
m
ob
il
e
S
M
S
s
e
r
vi
c
e
s
,
e
m
pl
oyi
ng
two s
ophi
s
ti
c
a
te
d
c
la
s
s
if
ic
a
ti
on
a
lg
or
it
hm
s
-
r
a
ndom
f
or
e
s
t
a
nd
ve
c
to
r
m
a
c
hi
ne
[
25]
,
[
29]
,
[
30
]
.
T
he
a
ut
hor
s
'
ut
i
li
z
a
ti
on
of
c
la
s
s
if
ic
a
ti
on
a
lg
or
it
h
m
s
w
a
s
th
or
oughly
in
ve
s
ti
ga
te
d
to
une
a
r
th
vul
ne
r
a
bi
li
ti
e
s
in
s
m
is
hi
ng
d
e
te
c
ti
on.
T
he
s
tu
di
e
s
c
r
a
f
te
d
di
v
e
r
s
e
m
ode
ls
a
nd
m
obi
le
a
ppl
ic
a
ti
ons
ta
il
or
e
d
to
a
ddr
e
s
s
th
e
id
e
nt
if
ie
d
is
s
ue
s
,
in
te
gr
a
ti
ng
m
a
c
hi
ne
le
a
r
ni
ng
to
e
nha
nc
e
s
m
is
hi
ng
d
e
te
c
ti
on
pr
oc
e
s
s
e
s
in
f
r
a
udul
e
nt
w
e
b
pa
ge
s
a
nd
S
M
S
m
e
s
s
a
ge
s
[
24]
,
[
30]
–
[
33]
.
A
m
a
jo
r
it
y
of
th
e
a
r
ti
c
le
s
a
r
ti
c
ul
a
te
th
e
ir
m
e
th
odol
ogi
c
a
l
a
ppr
oa
c
h,
a
ppl
yi
ng
c
la
s
s
if
ic
a
ti
on
a
lg
or
it
hm
s
f
or
th
e
a
na
ly
s
is
of
w
e
b
pa
ge
s
,
e
m
a
il
m
e
s
s
a
ge
s
,
m
a
li
c
io
us
U
R
L
s
, Q
R
c
ode
s
,
a
nd mobi
le
a
ppl
ic
a
ti
ons
. F
ig
ur
e
3 i
ll
us
tr
a
te
s
t
hr
e
e
e
xa
m
pl
e
s
of
s
m
is
hi
ng
.
F
ig
ur
e
3.
S
m
is
hi
ng
a
tt
a
c
k pr
oc
e
s
s
[
34]
S
m
i
s
hi
ng
op
e
r
a
ti
o
n
s
[
3
4]
vi
a
t
e
x
t
m
e
s
s
a
g
e
s
s
t
a
r
t
w
it
h
a
n
S
M
S
f
r
om
t
he
a
t
ta
c
k
e
r
t
ha
t
in
c
l
ud
e
s
a
U
R
L
,
e
m
a
il
, or
ph
on
e
num
be
r
.
C
li
c
ki
ng
o
n t
h
e
l
in
k
r
e
d
ir
e
c
t
s
t
he
u
s
e
r
t
o a
da
ng
e
r
o
u
s
w
e
b
s
it
e
.
O
n
th
is
s
it
e
, a
f
or
m
w
it
h
1
4
3
1
9
6
2
3
4
2
1
0
2
4
6
8
10
2018
2019
2020
2021
2022
2023
T
y
pe
of
S
t
u
dy
Y
e
a
r
of
pu
bl
i
c
a
t
i
on
C
onf
e
r
e
nc
e
pa
pe
r
A
r
t
i
c
l
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
A
r
ti
f
I
nt
e
ll
I
S
S
N
:
2252
-
8938
A
ppl
ic
at
io
n of
c
la
s
s
if
ic
at
io
n al
gor
it
hm
s
f
or
s
m
i
s
hi
ng de
te
c
ti
on
on m
obi
le
…
(
D
y
la
n F
ar
e
dh C
al
e
r
o Si
nc
he
)
3755
a
s
upp
o
s
e
d
gi
f
t
is
pr
e
s
e
n
te
d,
a
s
ki
n
g
th
e
vi
c
t
im
f
or
p
e
r
s
o
na
l
in
f
or
m
a
t
io
n
,
s
uc
h
a
s
b
a
n
k
de
ta
il
s
.
A
lt
e
r
n
a
ti
v
e
ly
,
th
e
m
a
l
ic
i
ou
s
m
e
s
s
a
g
e
m
a
y
c
on
ta
in
a
li
n
k t
h
a
t
do
w
nl
oa
d
s
a
f
i
le
t
o
t
h
e
v
ic
ti
m
'
s
d
e
vi
c
e
[
29]
,
[
3
3]
,
[
3
5]
.
V
a
r
io
us
m
ode
ls
[
36]
–
[
40]
w
e
r
e
e
m
pl
oye
d
on
a
f
e
a
tu
r
e
m
a
tr
ix
ge
ne
r
a
te
d
f
r
om
a
da
ta
s
e
t
us
in
g
c
ount
ve
c
to
r
iz
e
r
s
a
nd
te
r
m
f
r
e
que
nc
y
-
in
ve
r
s
e
doc
um
e
nt
f
r
e
que
nc
y
(
T
F
I
D
F
)
.
T
he
be
nc
hm
a
r
k
m
ode
l,
n
a
iv
e
-
B
a
ye
s
m
ul
ti
nom
ia
l,
de
m
ons
tr
a
te
d
s
ubopti
m
a
l
pe
r
f
or
m
a
nc
e
,
w
he
r
e
a
s
r
a
ndom
f
or
e
s
t
e
xc
e
ll
e
d
w
it
h
94.86%
a
c
c
ur
a
c
y
in
c
ount
ve
c
to
r
iz
a
ti
on
a
nd
a
n
e
ve
n
m
or
e
im
pr
e
s
s
iv
e
99.86%
a
c
c
ur
a
c
y
w
it
h
T
F
I
D
F
.
T
a
bl
e
6
il
lu
s
tr
a
te
s
th
e
pe
r
f
or
m
a
nc
e
of
th
e
s
a
m
e
m
ode
l
us
in
g
th
e
T
F
I
D
F
ve
c
to
r
iz
a
ti
o
n
te
c
hni
que
.
U
nl
ik
e
th
e
ot
he
r
m
ode
ls
,
r
a
ndom
f
or
e
s
t
e
xc
e
ll
e
d, a
c
hi
e
vi
ng a
n
a
c
c
ur
a
c
y r
a
te
of
99.86%
.
T
a
bl
e
6. M
od
e
l
pe
r
f
or
m
a
nc
e
s
w
it
h T
F
I
D
F
ve
c
to
r
iz
a
ti
on
M
ode
l
T
r
a
i
ni
ng t
i
m
e
A
c
c
ur
a
c
y
AUC
F1
-
s
c
or
e
L
og
-
l
os
s
M
ul
t
i
nom
i
a
l
na
i
ve
B
a
ye
s
4.75 m
s
0.8982
0.8986
0.9066
3.51
L
ogi
s
t
i
c
r
e
gr
e
s
s
i
on
74.3 m
s
0.9857
0.9857
0.9856
0.49
S
V
M
671
ms
0.9966
0.9965
0.9965
0.11
K
-
ne
a
r
e
s
t
ne
i
ghbor
s
2.39 m
s
0.9864
0.9864
0.9865
0.46
R
a
ndom
f
or
e
s
t
1.7 s
0.9986
0.9986
0.9986
0.04
A
da
B
oos
t
2.07 s
0.9975
0.9972
0.9972
0.09
E
xt
r
a
t
r
e
e
c
l
a
s
s
i
f
i
e
r
1.99 s
0.9984
0.9984
0.9984
0.05
3.2
.1.
R
Q
1.
Wh
at
ar
e
t
h
e
s
p
e
c
i
f
ic
va
r
i
an
t
s
o
f
m
ob
il
e
p
h
i
s
h
in
g
t
h
at
h
av
e
b
e
e
n
u
s
e
d
a
s
t
h
e
ob
j
e
c
t
o
f
s
t
u
d
y
?
T
hi
r
ty
-
s
ix
a
r
ti
c
le
s
und
e
r
w
e
nt
th
or
ough
e
xa
m
in
a
ti
on,
e
nc
o
m
pa
s
s
in
g
s
tu
di
e
s
th
a
t
e
xpl
or
e
d
th
e
de
te
c
ti
on
of
phi
s
hi
ng
a
c
r
os
s
di
ve
r
s
e
dom
a
in
s
[
24]
–
[
27]
.
T
he
s
e
dom
a
in
s
in
c
lu
de
d
s
m
is
hi
ng
a
tt
a
c
ks
vi
a
e
m
a
il
s
a
nd
S
M
S
[
28]
–
[
33]
,
[
35]
,
[
41
]
–
[
44]
,
phi
s
hi
ng
de
te
c
ti
on
of
s
pa
m
m
e
s
s
a
ge
s
hous
in
g
m
a
li
c
io
u
s
U
R
L
s
[
45]
–
[
52]
,
phi
s
hi
ng
vi
a
Q
R
c
ode
s
[
52]
,
a
nd
phi
s
hi
ng
d
e
te
c
ti
on
w
it
hi
n
m
obi
le
a
ppl
ic
a
ti
ons
[
53]
,
[
54]
.
R
e
m
a
r
ka
bl
y, t
he
a
r
ti
c
le
s
pr
im
a
r
il
y e
la
bor
a
te
d on the
us
e
of
m
a
c
hi
ne
l
e
a
r
ni
ng t
e
c
hni
que
s
t
o de
te
c
t
a
nd pr
e
ve
nt
phi
s
hi
ng
a
tt
a
c
ks
a
nd
th
e
ir
va
r
ia
ti
ons
on
m
obi
le
de
vi
c
e
s
.
T
he
y
le
ve
r
a
ge
d
e
xi
s
ti
ng
c
la
s
s
if
ic
a
ti
on
a
lg
or
it
hm
s
w
hi
le
a
ls
o pr
opos
in
g i
nnova
ti
ve
a
ppl
ic
a
ti
on
s
.
F
ol
lo
w
in
g t
he
s
e
i
ni
ti
a
l
in
ve
s
ti
ga
ti
ons
, s
ubs
e
que
nt
s
tu
di
e
s
f
oc
us
e
d s
pe
c
if
ic
a
ll
y on a
na
ly
z
in
g
s
m
is
hi
ng
[
30]
,
[
31]
,
[
33
]
,
[
35]
,
[
41]
–
[
46]
,
[
49]
,
[
55
]
.
M
or
e
ove
r
,
T
a
b
le
6
pr
ovi
de
s
a
de
ta
il
e
d
br
e
a
kdown
of
th
e
c
la
s
s
if
ic
a
ti
on
a
lg
or
it
hm
s
m
os
t
c
om
m
onl
y
e
m
pl
oye
d
in
th
e
s
e
s
t
udi
e
s
.
S
ubs
e
qu
e
nt
ly
,
a
s
s
e
s
s
m
e
nt
s
w
e
r
e
c
a
r
r
ie
d
out
to
a
s
s
e
s
s
th
e
r
e
li
a
bi
li
ty
a
nd
le
gi
ti
m
a
c
y
of
w
e
b
pa
ge
s
,
o
nl
in
e
s
e
r
vi
c
e
s
,
a
nd
s
p
a
m
m
e
s
s
a
ge
s
hou
s
in
g
m
a
li
c
io
us
U
R
L
s
[
24]
,
[
26]
,
[
28]
,
[
29]
,
[
32]
,
[
47
]
,
[
48]
,
[
50]
,
[
5
6]
.
N
ot
e
w
or
th
y
is
th
e
obs
e
r
va
ti
on
th
a
t
th
e
c
r
ux
of
th
e
s
tu
dy
obj
e
c
t,
a
ddr
e
s
s
e
d
in
th
e
pr
opo
s
e
d
s
ol
ut
io
n
s
,
pe
r
ta
i
ns
to
s
m
is
hi
ng
,
w
it
h
44%
of
th
e
to
ta
l
a
r
ti
c
le
s
r
e
f
e
r
e
nc
in
g
th
is
s
pe
c
if
ic
ty
pe
of
phi
s
hi
ng.
T
hi
s
c
ha
ll
e
nge
s
te
m
s
f
r
om
th
e
in
he
r
e
nt
di
f
f
ic
ul
ty
in
id
e
nt
i
f
yi
ng
s
m
is
hi
ng
,
gi
ve
n
th
e
ir
c
ons
tr
a
in
e
d
c
ont
e
nt
a
nd
th
e
di
ve
r
s
e
a
r
r
a
y
of
c
ha
r
a
c
te
r
s
e
m
pl
oye
d
by
a
tt
a
c
ke
r
s
,
a
lo
ng
w
it
h U
R
L
s
t
ha
t
c
lo
s
e
ly
m
im
ic
l
e
gi
ti
m
a
te
pa
ge
s
.
3.2.2.
R
Q
2.
Wh
at
w
e
r
e
t
h
e
s
ol
u
t
io
n
s
i
m
p
le
m
e
n
t
e
d
t
h
r
ou
g
h
t
h
e
c
la
s
s
i
f
ic
at
io
n
al
gor
it
h
m
s
f
or
s
m
is
h
in
g
d
e
t
e
c
t
io
n
?
I
n e
a
c
h phis
hi
ng s
c
e
na
r
io
, w
e
c
onduc
t
e
d c
om
pr
e
he
ns
iv
e
c
om
pa
r
is
ons
a
m
ong the
pr
opos
e
d s
ol
ut
io
ns
.
O
ur
a
na
ly
s
is
unve
il
e
d
th
a
t
m
or
e
th
a
n
ha
lf
of
th
e
a
r
ti
c
le
s
le
v
e
r
a
ge
m
a
c
hi
ne
-
le
a
r
ni
ng
te
c
hni
que
s
to
upda
te
da
ta
ba
s
e
s
f
or
th
e
de
te
c
ti
on
of
phi
s
hi
ng
or
s
m
is
hi
ng
.
T
he
s
tu
di
e
s
c
ons
i
s
te
nt
ly
e
m
pl
oy
w
id
e
ly
r
e
c
ogni
z
e
d
c
la
s
s
if
ic
a
ti
on
a
lg
or
it
hm
s
,
s
uc
h
a
s
r
a
ndom
f
or
e
s
t,
de
c
is
io
n
tr
e
e
,
s
uppor
t
ve
c
to
r
m
a
c
hi
ne
,
lo
gi
s
ti
c
r
e
gr
e
s
s
io
n,
n
a
iv
e
B
a
ye
s
,
a
nd
a
r
ti
f
ic
ia
l
ne
ur
a
l
ne
twor
k
[
27]
–
[
35]
,
[
41
]
–
[
46]
,
[
49]
–
[
51
]
,
[
53
]
,
[
56
]
.
T
he
a
ut
hor
s
m
e
ti
c
ul
ous
ly
e
lu
c
id
a
te
d
th
e
ir
tr
a
in
in
g
m
e
th
odol
ogi
e
s
,
pr
ovi
di
ng
va
lu
a
bl
e
in
s
ig
ht
s
in
to
th
e
ir
a
ppr
oa
c
he
s
a
nd
th
e
im
pl
e
m
e
nt
a
ti
on
of
th
e
ir
p
r
opos
e
d
s
ol
ut
io
ns
.
F
ur
th
e
r
m
o
r
e
,
r
e
s
e
a
r
c
he
r
s
in
tr
oduc
e
d
m
obi
le
a
ppl
ic
a
ti
ons
de
s
ig
ne
d
e
xpl
ic
it
ly
f
or
s
m
is
hi
ng
id
e
nt
if
ic
a
ti
on
[
53]
,
[
54]
.
T
he
y
of
f
e
r
e
d
a
n
in
-
de
pt
h
ove
r
vi
e
w
of
th
e
m
os
t
f
r
e
que
nt
ly
ut
il
iz
e
d
te
c
hni
que
s
f
or
im
pl
e
m
e
nt
in
g
a
nd
c
a
te
g
or
iz
in
g
phi
s
hi
ng,
in
tr
oduc
in
g
a
n
in
nova
ti
ve
a
ppr
oa
c
h
known a
s
th
e
gr
a
phi
c
a
l
u
s
e
r
in
te
r
f
a
c
e
(
G
U
I
)
-
s
qua
tt
in
g
a
tt
a
c
k
to
a
s
s
e
s
s
m
obi
le
a
ppl
ic
a
ti
on
in
te
r
f
a
c
e
s
[
54]
.
C
ons
e
que
nt
ly
,
th
e
pr
opos
e
d
s
ol
ut
io
ns
a
c
r
o
s
s
va
r
io
us
s
tu
di
e
s
e
xhi
bi
t
va
r
ia
ti
ons
ba
s
e
d
on
th
e
s
pe
c
if
ic
obj
e
c
ti
ve
s
a
im
e
d
a
t
a
ddr
e
s
s
in
g
th
e
pr
obl
e
m
.
A
s
ubs
ta
nt
ia
l
s
e
gm
e
nt
of
th
e
s
c
r
ut
in
iz
e
d
s
ol
ut
io
ns
unde
r
w
e
nt
te
s
ti
ng
in
c
ont
r
ol
le
d
e
xpe
r
im
e
nt
a
l
s
e
tt
in
gs
,
yi
e
ld
in
g
c
ons
i
s
t
e
nt
ly
pos
it
iv
e
out
c
om
e
s
.
T
a
bl
e
7
s
u
c
c
in
c
tl
y
pr
e
s
e
nt
s
th
e
pr
opos
e
d
s
ol
ut
io
ns
a
nd
th
e
ir
r
e
s
pe
c
ti
ve
tr
a
in
in
g
pr
oc
e
s
s
e
s
,
s
how
in
g
th
a
t
r
e
s
e
a
r
c
he
r
s
pr
e
s
e
nt
ne
w
m
ode
ls
de
s
ig
ne
d
to
a
ddr
e
s
s
va
r
io
us
phi
s
hi
ng
a
tt
a
c
k
s
c
e
n
a
r
io
s
.
H
ow
e
ve
r
,
it
is
hi
ghl
ig
ht
e
d
th
a
t
th
e
c
la
s
s
if
ic
a
ti
on a
lg
or
it
hm
s
i
m
pl
e
m
e
nt
e
d a
r
e
m
o
s
tl
y t
he
m
os
t
us
e
d
a
m
ong the
s
tu
di
e
s
a
n
a
ly
z
e
d.
3.2.3. RQ3.
Wh
at
w
e
r
e
t
h
e
r
e
s
u
lt
s
ob
t
ai
n
e
d
b
y ap
p
ly
in
g
t
h
e
s
e
p
r
op
os
e
d
s
ol
u
t
io
n
s
?
S
e
ve
r
a
l
s
tu
di
e
s
s
im
il
a
r
ly
e
m
pl
oye
d
c
la
s
s
if
ic
a
ti
on
a
lg
or
it
hm
s
w
hi
le
a
ddr
e
s
s
in
g
va
r
io
us
m
obi
le
a
tt
a
c
k
s
c
e
na
r
io
s
.
T
he
y
a
ppl
ie
d
m
a
c
hi
ne
le
a
r
ni
ng
te
c
hni
que
s
to
e
va
lu
a
te
th
e
ir
e
f
f
ic
a
c
y
or
e
nha
nc
e
th
e
ir
r
e
s
pe
c
ti
v
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8938
I
nt
J
A
r
ti
f
I
nt
e
ll
, V
ol
. 13, No. 4, D
e
c
e
m
be
r
2024:
3750
-
3760
3756
s
ol
ut
io
ns
,
a
im
in
g
to
a
c
hi
e
v
e
e
l
e
va
te
d
a
c
c
ur
a
c
y
le
ve
ls
in
s
m
is
h
in
g
de
te
c
ti
on
[
50]
,
r
e
s
ul
ti
ng
in
a
n
im
pr
e
s
s
iv
e
99.57%
a
c
c
ur
a
c
y
r
a
te
.
T
a
bl
e
8
c
om
pr
e
he
ns
iv
e
ly
s
um
m
a
r
iz
e
s
t
he
a
c
c
ur
a
c
y
le
ve
ls
obs
e
r
ve
d
in
a
ll
th
e
s
tu
di
e
s
a
na
ly
z
e
d.
T
hi
s
ta
bl
e
pr
e
s
e
nt
s
th
e
r
e
s
ul
ts
obt
a
in
e
d
in
e
a
c
h
s
t
udy,
a
lo
ng
w
it
h
it
s
c
or
r
e
s
ponding
s
m
is
hi
ng
de
te
c
ti
on
a
c
c
ur
a
c
y.
I
m
por
ta
nt
ly
,
s
tu
di
e
s
in
te
gr
a
ti
ng
c
la
s
s
if
ic
a
ti
on
a
lg
or
it
hm
s
w
it
h
a
r
ti
f
ic
ia
l
in
te
ll
ig
e
nc
e
pr
e
dom
in
a
nt
ly
a
c
hi
e
ve
d
r
a
te
s
e
xc
e
e
di
ng
th
e
90%
th
r
e
s
hol
d.
T
hi
s
hi
ghl
ig
ht
s
th
e
e
f
f
e
c
ti
ve
ne
s
s
of
th
e
te
c
hni
que
s
us
e
d
to
de
te
c
t
a
nd
r
e
c
ogni
z
e
s
m
is
hi
ng
a
tt
a
c
k
s
.
T
he
ove
r
a
ll
a
ve
r
a
ge
,
pr
ovi
de
d
a
t
th
e
e
nd,
i
s
95.39%
,
s
ig
ni
f
yi
ng
a
r
e
m
a
r
ka
bl
e
le
ve
l
of
r
e
li
a
bi
li
ty
a
nd
f
ir
m
pe
r
f
or
m
a
nc
e
in
id
e
nt
i
f
yi
ng
phi
s
hi
ng
a
nd
it
s
m
obi
le
-
or
ie
nt
e
d va
r
ia
nt
s
, i
nc
lu
di
ng
s
m
is
hi
ng
.
T
a
bl
e
7. P
r
opos
e
d s
ol
ut
io
n
s
a
nd t
r
a
in
in
g pr
oc
e
s
s
R
e
f
e
r
e
nc
e
P
r
opos
e
d S
ol
ut
i
ons
T
r
a
i
ni
ng pr
oc
e
s
s
[
24]
–
[
27]
D
e
e
p l
e
a
r
ni
ng t
e
c
hni
que
s
a
nd
e
xpe
r
t
s
ys
t
e
m
s
f
or
phi
s
hi
ng a
nd m
a
l
w
a
r
e
de
t
e
c
t
i
on
A
r
t
i
f
i
c
i
a
l
ne
ur
a
l
ne
t
w
or
ks
[
28]
–
[
33]
,
[
35]
, [
41]
, [
44
]
H
ybr
i
d f
r
a
m
e
w
or
k f
o
r
f
e
a
t
ur
e
e
xt
r
a
c
t
i
on f
r
om
phi
s
hi
ng
e
m
a
i
l
a
nd S
M
S
t
e
xt
s
C
onvol
ut
i
ona
l
ne
ur
a
l
ne
t
w
or
ks
[
45]
–
[
51]
U
R
L
s
m
i
s
hi
ng
c
l
a
s
s
i
f
i
e
r
i
n S
P
A
M
m
e
s
s
a
g
e
s
S
P
A
M
l
og ba
nk w
i
t
h m
a
l
i
c
i
ous
U
R
L
s
[
53]
, [
54]
GUI
-
S
qua
t
t
i
ng a
t
t
a
c
k m
obi
l
e
a
ppl
i
c
a
t
i
on
C
onvol
ut
i
ona
l
ne
ur
a
l
ne
t
w
or
ks
[
55]
T
w
o
-
di
m
e
ns
i
ona
l
c
ode
(
Q
R
)
m
e
t
hod
S
V
M
, pyr
a
m
i
da
l
f
unc
t
i
on ne
t
w
or
k (
F
P
N
)
T
a
bl
e
8. E
vi
de
nc
e
of
p
hi
s
hi
ng mi
ti
ga
ti
on e
f
f
e
c
ti
ve
ne
s
s
a
nd r
e
s
u
lt
s
R
e
f
e
r
e
nc
e
P
r
e
c
i
s
i
on
(%)
M
e
t
hodol
ogi
e
s
us
e
d
G
upt
a
e
t
al
.
[
50]
99
.
57
F
our
m
a
c
hi
ne
l
e
a
r
ni
ng a
l
gor
i
t
hm
s
w
e
r
e
e
va
l
ua
t
e
d:
r
a
ndom
f
or
e
s
t
, k
-
ne
a
r
e
s
t
ne
i
ghbor
s
,
l
ogi
s
t
i
c
r
e
gr
e
s
s
i
on a
nd s
uppor
t
ve
c
t
or
m
a
c
hi
ne
.
J
a
i
n
e
t
al
.
[
46]
99
.
03
G
r
a
di
e
nt
boos
t
e
d de
c
i
s
i
on t
r
e
e
a
l
gor
i
t
hm
w
a
s
u
s
e
d.
J
a
i
n a
nd G
upt
a
[
51]
98
.
74
E
va
l
ua
t
i
on of
m
e
s
s
a
ge
da
t
a
s
e
t
, t
he
"
r
a
ndom
f
or
e
s
t
" c
l
a
s
s
i
f
i
c
a
t
i
on a
l
gor
i
t
hm
w
a
s
us
e
d.
U
l
f
a
t
h
e
t
al
.
[
31]
98
.
57
C
onvol
ut
i
ona
l
ne
ur
a
l
ne
t
w
or
ks
w
e
r
e
i
m
pl
e
m
e
nt
e
d.
S
ha
a
ba
n
e
t
al
.
[
49]
98
.
50
A
r
t
i
f
i
c
i
a
l
ne
ur
a
l
ne
t
w
or
k (
A
N
N
)
c
l
a
s
s
i
f
i
c
a
t
i
on a
l
gor
i
t
hm
.
A
ka
nde
e
t
al
.
[
41]
98
.
42
C
l
a
s
s
i
f
i
c
a
t
i
on a
l
gor
i
t
hm
s
:
R
I
P
P
E
R
a
nd C
4.5.
G
hour
a
bi
e
t
al
.
[
29]
98
.
37
C
om
bi
na
t
i
on
of
t
w
o
de
e
p
l
e
a
r
ni
ng
m
e
t
hods
s
hor
t
a
nd
l
ong
m
e
m
or
y
ne
ur
a
l
ne
t
w
or
ks
C
onvol
ut
i
ona
l
ne
ur
a
l
ne
t
w
or
ks
a
nd
l
ong s
hor
t
-
t
e
r
m
m
e
m
or
y (
L
S
T
M
)
.
Y
e
r
i
m
a
a
nd B
a
s
ha
r
[
45]
98
.
00
R
a
ndom
f
or
e
s
t
a
nd de
c
i
s
i
on t
r
e
e
c
l
a
s
s
i
f
i
c
a
t
i
on a
l
gor
i
t
hm
.
M
i
s
hr
a
a
nd S
oni
[
30]
97
.
93
N
e
ur
a
l
ne
t
w
or
ks
w
i
t
h ba
c
k pr
opa
ga
t
i
on a
l
gor
i
t
hm
.
M
a
hda
vi
f
a
r
a
nd
G
hor
ba
ni
[
26]
97
.
50
I
t
us
e
s
a
n a
l
gor
i
t
hm
c
a
l
l
e
d de
e
p i
nf
e
r
e
nc
e
j
us
t
i
f
i
c
a
t
i
on (
D
I
J
)
t
o e
xt
r
a
c
t
r
e
f
i
ne
d r
ul
e
s
f
r
om
a
t
r
a
i
ne
d de
e
p ne
ur
a
l
ne
t
w
or
k.
H
a
yne
s
e
t
al
.
[
24]
96
.
00
A
r
t
i
f
i
c
i
a
l
ne
ur
a
l
ne
t
w
or
ks
w
e
r
e
us
e
d.
Z
oui
na
a
nd O
ut
t
a
j
[
27]
95
.
80
T
he
s
m
i
s
hi
ng
de
t
e
c
t
i
on ba
s
e
d on
c
or
r
e
l
a
t
i
on a
l
gor
i
t
hm
(
S
m
i
D
C
A
)
m
ode
l
i
nc
or
por
a
t
e
s
di
m
e
ns
i
ona
l
i
t
y r
e
duc
t
i
on, ba
s
e
d on t
he
r
a
ndom
f
or
e
s
t
c
l
a
s
s
i
f
i
c
a
t
i
on a
l
gor
i
t
hm
.
Y
a
o
e
t
al
.
[
55]
94
.
70
F
a
s
t
e
r
r
e
gi
on
-
ba
s
e
d c
onvol
ut
i
ona
l
ne
ur
a
l
ne
t
w
or
k (
R
-
C
N
N
)
.
J
a
i
n
e
t
al
.
[
25]
93
.
85
C
l
a
s
s
i
f
i
c
a
t
i
on a
l
gor
i
t
hm
s
l
ogi
s
t
i
c
r
e
gr
e
s
s
i
on, de
c
i
s
i
on t
r
e
e
a
nd r
a
ndom
f
or
e
s
t
.
M
a
o
e
t
al
.
[
47]
93
.
70
T
he
c
l
a
s
s
i
f
i
e
r
s
e
va
l
ua
t
e
d
a
r
e
A
da
B
oos
t
(
A
B
)
, r
a
ndom
f
or
e
s
t
, s
upe
r
ve
c
t
or
m
a
c
h
i
ne
a
nd
de
c
i
s
i
on t
r
e
e
)
.
Z
a
w
a
nd V
a
s
uponga
yya
[
28]
93
.
66
V
a
r
i
a
bi
l
i
t
y of
phi
s
hi
ng a
t
t
a
c
ks
, f
a
l
s
e
pos
i
t
i
ve
s
a
nd f
a
l
s
e
ne
g
a
t
i
ve
s
.
S
onow
a
l
a
nd
K
uppus
a
m
y
[
44]
93
.
37
S
m
i
D
C
A
m
ode
l
i
nc
or
por
a
t
e
s
di
m
e
ns
i
ona
l
i
t
y r
e
duc
t
i
on, us
e
of
r
a
ndom
f
or
e
s
t
c
l
a
s
s
i
f
i
c
a
t
i
on a
l
gor
i
t
hm
.
O
z
ke
r
a
nd S
a
hi
ngoz
[
48]
92
.
86
R
a
ndom
f
or
e
s
t
, s
uppor
t
ve
c
t
or
m
a
c
hi
ne
s
, l
ogi
s
t
i
c
r
e
gr
e
s
s
i
on a
nd de
c
i
s
i
on t
r
e
e
.
C
a
t
a
l
e
t
al
.
[
56]
92
.
70
T
w
o c
l
a
s
s
i
f
i
c
a
t
i
on a
l
gor
i
t
hm
s
w
e
r
e
i
m
pl
e
m
e
nt
e
d:
S
upe
r
ve
c
t
or
m
a
c
hi
ne
a
nd r
a
ndom
f
or
e
s
t
.
K
or
km
a
z
e
t
al
.
[
32]
92
.
11
L
ogi
s
t
i
c
r
e
gr
e
s
s
i
on, r
a
ndom
f
or
e
s
t
a
nd de
c
i
s
i
on t
r
e
e
.
J
a
i
n a
nd G
upt
a
[
43]
92
.
00
T
he
c
l
a
s
s
i
f
i
c
a
t
i
on a
l
gor
i
t
hm
s
us
e
d e
v
a
l
ua
t
e
d de
c
i
s
i
on t
r
e
e
s
w
i
t
h R
I
P
P
E
R
.
B
a
l
i
m
a
nd G
una
l
[
54]
83
.
30
"G
U
I
-
S
qua
t
t
i
ng a
t
t
a
c
k", w
hi
c
h us
e
s
i
m
a
ge
pr
oc
e
s
s
i
ng a
nd de
e
p l
e
a
r
ni
ng ba
s
e
d
on
c
onvol
ut
i
ona
l
ne
ur
a
l
ne
t
w
or
ks
.
G
oe
l
a
nd J
a
i
n
[
42]
-
P
r
opos
e
d
s
m
i
s
hi
ng
-
c
l
a
s
s
i
f
i
e
r
m
ode
l
doe
s
not
pr
e
s
e
nt
a
c
c
ur
a
c
y r
e
s
ul
t
s
.
C
he
n
e
t
al
.
[
53]
-
T
he
r
e
vi
e
w
e
d s
t
udy di
d not
i
m
pl
e
m
e
nt
a
c
l
a
s
s
i
f
i
c
a
t
i
on a
l
gor
i
t
hm
.
I
n
th
e
f
ol
lo
w
in
g
s
tu
dy
[
34]
,
th
e
f
ol
lo
w
in
g
m
e
tr
ic
s
w
e
r
e
im
pl
e
m
e
nt
e
d
to
m
e
a
s
ur
e
th
e
pe
r
f
or
m
a
nc
e
a
nd
e
f
f
e
c
ti
ve
ne
s
s
of
th
e
s
e
c
ur
it
y
m
ode
l.
T
a
bl
e
9
s
how
s
th
e
e
va
lu
a
ti
on
m
e
tr
ic
s
,
w
hi
c
h
s
how
th
e
e
va
lu
a
ti
on
of
th
e
pe
r
f
or
m
e
d
m
ode
ls
,
c
ove
r
in
g
th
e
f
ol
lo
w
in
g
pe
r
f
or
m
a
nc
e
m
e
tr
ic
s
[
34]
,
[
57]
,
[
58]
.
A
,
tr
ue
pos
it
iv
e
s
(
T
P
)
m
e
a
n
a
c
c
ur
a
te
ly
pr
e
di
c
te
d
m
a
lwa
r
e
in
s
ta
nc
e
s
,
w
hi
le
f
a
ls
e
n
e
ga
ti
ve
s
(
F
N
)
de
not
e
m
i
s
c
la
s
s
if
ie
d
m
a
lwa
r
e
in
s
ta
nc
e
s
.
T
r
ue
pos
it
iv
e
r
a
te
(
T
P
R
)
s
ta
nds
f
or
r
e
c
ove
r
y
a
nd
s
e
ns
it
iv
it
y.
B
,
f
a
ls
e
pos
it
iv
e
s
(
F
P
)
r
e
pr
e
s
e
nt
th
e
c
ount
of
in
c
or
r
e
c
tl
y
pr
e
di
c
te
d
be
ni
gn
c
la
s
s
if
ic
a
ti
ons
.
C
,
F
-
m
e
a
s
ur
e
is
u
s
e
d
f
or
c
om
pa
r
a
ti
ve
pe
r
f
or
m
a
nc
e
a
na
ly
s
is
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
A
r
ti
f
I
nt
e
ll
I
S
S
N
:
2252
-
8938
A
ppl
ic
at
io
n of
c
la
s
s
if
ic
at
io
n al
gor
it
hm
s
f
or
s
m
i
s
hi
ng de
te
c
ti
on
on m
obi
le
…
(
D
y
la
n F
ar
e
dh C
al
e
r
o Si
nc
he
)
3757
T
a
bl
e
9. M
od
e
l
e
va
lu
a
ti
on me
tr
ic
s
N
.º
E
va
l
ua
t
i
on m
e
t
r
i
c
s
F
or
m
ul
a
t
i
on of
m
e
t
r
i
c
s
A
A
c
c
ur
a
c
y
TP
+
TN
TP
+
TF
+
TN
+
FN
B
P
r
e
c
i
s
i
on
TP
TP
+
FP
C
F
-
m
e
a
s
ur
e
2
.
P
r
e
c
i
s
i
on
P
r
e
c
i
s
i
on
+
R
e
c
a
l
l
3.2.4.
R
Q
4. Wh
at
p
r
ac
t
ic
e
s
ar
e
r
e
c
o
m
m
e
n
d
e
d
f
or
s
m
is
h
in
g
d
e
t
e
c
t
io
n
an
d
m
it
ig
at
io
n
?
T
hi
s
s
e
c
ti
on
pr
e
s
e
nt
s
th
e
m
a
in
in
s
ig
ht
s
f
r
om
th
e
s
tu
di
e
s
c
on
duc
te
d,
w
hi
c
h
c
a
n
s
e
r
ve
a
s
va
lu
a
bl
e
c
ons
id
e
r
a
ti
ons
f
or
f
ut
ur
e
r
e
s
e
a
r
c
h.
T
he
s
e
in
s
ig
ht
s
pos
s
e
s
s
t
he
c
a
pa
c
it
y
to
a
id
in
f
or
m
ul
a
ti
ng
e
s
s
e
nt
ia
l
gui
de
li
ne
s
t
o i
m
pr
ove
s
m
is
hi
ng
de
te
c
ti
on, e
it
he
r
by i
nt
r
oduc
in
g i
nnova
ti
ve
m
e
th
odol
ogi
e
s
or
r
e
f
in
in
g e
xi
s
ti
ng
one
s
.
T
a
bl
e
10
li
s
ts
th
e
s
tu
di
e
s
th
a
t
de
s
e
r
ve
f
ur
th
e
r
e
xpl
or
a
ti
on,
a
s
r
e
c
om
m
e
nde
d
by
th
e
a
ut
hor
s
,
to
pr
ovi
de
a
m
or
e
c
om
pl
e
te
unde
r
s
ta
ndi
ng
of
th
e
pr
obl
e
m
a
ddr
e
s
s
e
d.
T
hi
s
ta
bl
e
hi
ghl
ig
ht
s
m
a
ny
r
e
c
om
m
e
nda
ti
ons
th
a
t
e
m
pha
s
iz
e
th
e
e
f
f
e
c
ti
ve
ne
s
s
of
u
s
in
g
m
a
c
hi
ne
le
a
r
ni
ng
te
c
hn
iq
ue
s
to
im
pr
ove
phi
s
hi
ng
d
e
te
c
ti
on
r
e
s
ul
t
s
.
F
ur
th
e
r
m
or
e
, i
t
s
ugge
s
ts
de
lv
in
g de
e
pe
r
i
nt
o t
hi
s
doma
in
t
o guide
f
ut
ur
e
r
e
s
e
a
r
c
h e
f
f
or
ts
.
T
a
bl
e
10. R
e
c
om
m
e
nda
ti
ons
f
or
s
m
is
hi
ng
de
te
c
ti
on
R
e
f
e
r
e
nc
e
R
e
c
om
m
e
nda
t
i
ons
[
25]
T
he
y r
e
c
om
m
e
nd i
nve
s
t
i
ga
t
i
ng t
he
us
e
of
e
ns
e
m
bl
e
l
e
a
r
ni
ng t
e
c
hni
que
s
,
s
uc
h a
s
B
a
ggi
ng a
nd B
oo
s
t
i
ng.
[
30]
U
s
e
e
f
f
i
c
i
e
nt
m
a
c
hi
ne
l
e
a
r
ni
ng a
l
gor
i
t
hm
s
t
o de
t
e
c
t
a
nd pr
e
ve
nt
s
m
i
s
hi
ng
.
[
45]
I
nve
s
t
i
ga
t
e
ot
he
r
t
ype
s
of
nove
l
t
y de
t
e
c
t
i
on m
ode
l
s
ba
s
e
d on s
e
m
i
-
s
upe
r
vi
s
e
d
m
a
c
hi
ne
l
e
a
r
ni
ng.
[
28]
A
ddr
e
s
s
m
or
e
a
da
pt
i
ve
t
e
c
hni
que
s
a
nd m
ode
l
s
f
or
a
ny dom
a
i
n w
he
r
e
s
m
i
s
hi
ng
oc
c
ur
s
.
[
55]
U
s
e
i
m
pr
ove
d l
ogo r
e
c
ogni
t
i
on t
e
c
hni
que
s
.
[
46]
U
s
i
ng c
ont
e
nt
a
na
l
ys
i
s
t
o be
t
t
e
r
r
e
c
ogni
z
e
pa
t
t
e
r
ns
t
o i
ndi
c
a
t
e
s
m
i
s
hi
ng
.
[
29]
P
e
r
f
or
m
a
na
l
ys
i
s
of
U
R
L
s
or
f
i
l
e
s
t
ha
t
a
r
e
a
t
t
a
c
he
d t
o S
M
S
m
e
s
s
a
ge
s
.
[
24]
R
e
gul
a
r
l
y upda
t
e
da
t
a
ba
s
e
s
of
know
n
s
m
i
s
hi
ng
s
i
t
e
s
.
[
31]
I
nt
r
oduc
e
s
i
gni
f
i
c
a
nt
ne
w
r
ul
e
s
t
ha
t
c
a
n i
m
pr
ove
t
he
t
r
ue
pos
i
t
i
ve
r
a
t
e
a
nd ove
r
a
l
l
t
a
r
ge
t
i
ng a
c
c
ur
a
c
y.
[
26]
U
s
e
a
c
om
bi
na
t
i
on of
de
e
p ne
ur
a
l
ne
t
w
or
ks
a
nd
e
xpe
r
t
s
ys
t
e
m
s
t
o i
m
pr
ove
t
he
a
c
c
ur
a
c
y a
nd r
obus
t
ne
s
s
of
t
he
s
y
s
t
e
m
s
.
[
44]
A
dd m
or
e
f
e
a
t
ur
e
s
a
nd us
e
ne
w
f
e
a
t
ur
e
s
e
l
e
c
t
i
on a
l
gor
i
t
hm
s
t
o i
m
pr
ove
a
c
c
ur
a
c
y.
[
27]
E
va
l
ua
t
e
t
he
s
i
z
e
of
t
he
U
R
L
, t
he
num
be
r
of
da
s
he
s
, dot
s
, num
e
r
i
c
I
P
c
ha
r
a
c
t
e
r
s
i
n t
he
U
R
L
.
3.3. Dis
c
u
s
s
io
n
T
he
s
c
op
e
of
a
r
ti
c
le
s
r
e
la
te
d
to
th
e
a
ppl
ic
a
ti
on
of
m
a
c
hi
ne
le
a
r
ni
ng
-
ba
s
e
d
c
la
s
s
if
ic
a
ti
on
a
lg
or
it
hm
s
f
or
s
m
is
hi
ng
de
te
c
ti
on
on
m
obi
le
de
vi
c
e
s
ha
s
s
ig
ni
f
ic
a
nt
ly
c
ont
r
ib
ut
e
d
to
th
e
de
ve
lo
pm
e
nt
of
th
is
w
or
k.
T
hi
s
di
s
c
us
s
io
n
e
n
c
om
pa
s
s
e
s
th
e
obt
a
in
e
d
r
e
s
ul
ts
a
bout
in
f
or
m
a
ti
on
s
e
le
c
ti
on
a
nd
r
e
vi
e
w
que
s
ti
ons
,
c
onduc
te
d
w
it
hi
n t
he
S
c
opus
a
nd A
R
D
I
da
ta
ba
s
e
s
. A
lt
hough we
f
ound c
o
m
m
ona
li
ti
e
s
a
m
ong a
r
ti
c
le
s
us
in
g ke
yw
or
ds
, i
t
be
c
a
m
e
e
vi
de
nt
th
a
t
th
e
y
la
c
k
e
d
a
s
pe
c
if
ic
e
m
pha
s
is
on
m
obi
le
de
vi
c
e
s
.
N
e
ve
r
th
e
le
s
s
,
th
e
out
c
om
e
s
yi
e
ld
e
d
pos
it
iv
e
r
e
s
ul
ts
th
a
t
w
e
r
e
c
ons
i
s
te
nt
w
it
h
th
e
pr
e
de
f
in
e
d
obj
e
c
ti
ve
s
of
th
e
r
e
vi
e
w
.
I
t'
s
w
or
th
not
in
g
th
a
t
m
os
t
s
tu
di
e
s
c
e
nt
e
r
e
d on
s
m
i
s
hi
ng
c
a
s
e
s
, ye
t
a
f
e
w
om
it
te
d e
xpl
ic
it
m
e
nt
io
ns
of
t
he
c
ont
e
xt
i
n w
hi
c
h t
he
y de
pl
oye
d
a
nd
e
va
lu
a
te
d
th
e
im
pl
e
m
e
nt
e
d
a
lg
or
it
hm
.
A
n
a
na
ly
s
is
of
m
a
c
hi
ne
le
a
r
ni
ng
te
c
hni
que
s
r
e
ve
a
le
d
a
pr
e
va
le
nt
ut
il
iz
a
ti
on
of
s
im
il
a
r
c
la
s
s
if
ic
a
ti
on
a
lg
or
it
hm
s
a
c
r
os
s
s
tu
di
e
s
,
le
a
di
ng
to
c
om
pa
r
a
bl
e
r
e
s
ul
ts
.
S
om
e
a
r
ti
c
le
s
s
pe
c
if
ic
a
ll
y
a
ddr
e
s
s
e
d
s
m
is
hi
ng
,
w
h
e
r
e
a
s
ot
he
r
s
d
e
lv
e
d
in
to
e
x
pl
or
in
g
nove
l
m
e
th
ods
f
or
phi
s
hi
ng
de
te
c
ti
on.
A
s
a
r
e
s
ul
t,
th
e
e
ndur
in
g
in
f
lu
e
nc
e
a
nd
a
ppl
ic
a
bi
li
ty
of
m
obi
l
e
a
ugm
e
nt
e
d
r
e
a
li
ty
m
a
y
s
ti
m
ul
a
te
a
ddi
ti
ona
l
e
vi
de
nc
e
-
ba
s
e
d pr
a
c
ti
c
a
l
r
e
s
e
a
r
c
h i
nt
o phis
hi
ng a
nd
s
m
is
hi
ng
a
tt
a
c
ks
.
T
he
a
ut
hor
s
e
m
pl
oy
e
d
te
c
hni
qu
e
s
a
nd
m
e
th
od
ol
ogi
e
s
to
a
dd
r
e
s
s
pr
e
va
l
e
nt
s
m
i
s
hi
ng
a
tt
a
c
k
s
a
nd
pr
opos
e
d
vi
a
bl
e
s
ol
u
ti
on
s
.
T
h
e
im
pl
e
m
e
nt
e
d
c
la
s
s
if
i
c
a
ti
on
a
lg
or
it
hm
s
ne
c
e
s
s
i
ta
t
e
a
c
o
nt
in
uo
us
da
t
a
s
tr
e
a
m
f
or
th
e
id
e
nt
if
i
c
a
ti
o
n
of
s
m
i
s
hi
ng
in
s
ta
n
c
e
s
o
n
m
ob
il
e
de
vi
c
e
s
.
T
hi
s
im
pa
c
t
i
s
e
vi
de
nt
a
c
r
o
s
s
a
ll
c
la
s
s
if
ic
a
ti
on
a
lg
or
it
hm
s
, a
lb
e
it
ha
vi
ng unde
r
g
one
va
r
io
us
t
e
s
ti
ng
m
e
th
od
ol
og
ie
s
,
yi
e
l
di
ng s
im
il
a
r
r
e
s
ul
t
s
. T
h
e
a
s
s
e
s
s
m
e
nt
of
th
e
s
e
f
in
di
ng
s
di
s
pl
a
ye
d
v
a
r
ia
bi
li
t
y
du
e
t
o
th
e
di
v
e
r
s
e
a
ppr
o
a
c
h
e
s
e
m
pl
o
ye
d
.
T
he
s
im
ul
a
ti
on
e
nc
om
pa
s
s
e
d
t
he
in
te
gr
a
t
io
n
of
a
c
h
a
r
a
c
te
r
d
a
ta
ba
s
e
f
or
t
he
r
e
c
ogn
it
io
n
of
b
ot
h
te
xt
ua
l
c
ont
e
nt
a
nd
im
a
ge
s
th
r
o
ugh
th
e
ut
il
iz
a
ti
on
of
a
r
ti
f
i
c
ia
l
in
t
e
ll
ig
e
nc
e
.
C
on
s
e
que
n
tl
y,
th
e
pr
op
os
e
d
s
ol
ut
io
ns
r
e
qu
ir
e
p
e
r
io
di
c
u
pda
t
e
s
to
e
f
f
e
c
ti
v
e
ly
di
s
c
e
r
n
e
vol
vi
ng
p
a
tt
e
r
ns
of
a
tt
a
c
k
s
.
T
h
e
pr
e
dom
i
na
nt
s
tr
a
te
gi
e
s
f
or
m
it
ig
a
ti
ng
s
m
is
h
in
g
pr
im
a
r
il
y
r
e
vol
ve
a
r
ound
e
nd
-
u
s
e
r
a
w
a
r
e
n
e
s
s
,
gi
v
e
n
th
e
ir
pi
vot
a
l
r
ol
e
a
s
th
e
pr
im
a
r
y
ta
r
ge
t
f
or
phi
s
hi
ng
a
tt
a
c
ke
r
s
.
T
he
e
xa
m
in
e
d
s
t
udi
e
s
a
dv
oc
a
t
e
f
or
th
e
e
xpl
or
a
ti
on
of
de
e
p
l
e
a
r
n
in
g
t
e
c
hni
que
s
,
pa
r
ti
c
ul
a
r
ly
t
he
ut
il
i
z
a
ti
o
n
of
c
onvol
ut
io
n
a
l
n
e
ur
a
l
ne
tw
or
ks
a
nd
r
e
c
ur
r
e
nt
ne
ur
a
l
n
e
twor
k
s
(
R
N
N
)
.
I
t
is
a
dv
is
a
bl
e
to
r
e
gul
a
r
l
y
upd
a
te
th
e
da
ta
b
a
s
e
of
de
t
e
c
ti
o
n
s
ys
t
e
m
s
to
e
nh
a
nc
e
a
c
c
ur
a
c
y
ov
e
r
ti
m
e
.
L
e
ve
r
a
gi
ng
th
e
a
dv
a
nt
a
ge
s
of
f
e
r
e
d
b
y
de
e
p
ne
ur
a
l
ne
t
w
or
k
s
c
a
n
s
ig
ni
f
ic
a
nt
ly
c
ont
r
ib
ut
e
t
o
th
e
i
de
nt
if
i
c
a
ti
on
of
S
M
S
s
pa
m
. A
ddi
ti
o
na
ll
y
,
th
e
r
e
is
a
not
a
bl
e
ga
p
i
n
th
e
e
xi
s
ti
ng
li
t
e
r
a
tu
r
e
c
onc
e
r
ni
ng
th
e
pr
e
ve
nt
io
n
of
c
ybe
r
c
r
im
e
in
m
obi
le
a
ppl
ic
a
ti
on
s
,
e
m
p
ha
s
iz
i
ng
t
he
ne
e
d f
or
f
ur
th
e
r
r
e
s
e
a
r
c
h i
n
th
i
s
a
r
e
a
d
ue
t
o
t
he
l
im
it
e
d num
be
r
o
f
s
tu
di
e
s
a
ddr
e
s
s
in
g
t
hi
s
c
r
u
c
ia
l
a
s
pe
c
t.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8938
I
nt
J
A
r
ti
f
I
nt
e
ll
, V
ol
. 13, No. 4, D
e
c
e
m
be
r
2024:
3750
-
3760
3758
H
ow
e
ve
r
,
s
im
il
a
r
to
a
ny
ot
he
r
r
e
vi
e
w
,
th
is
a
r
ti
c
le
doe
s
pos
e
s
o
m
e
li
m
it
a
ti
ons
.
T
he
s
e
in
c
lu
d
e
f
a
c
to
r
s
s
uc
h
a
s
th
e
s
e
le
c
ti
on
of
ke
yw
or
ds
a
nd
th
e
e
s
ta
bl
is
hm
e
nt
of
i
nc
lu
s
io
n
a
nd
e
xc
lu
s
io
n
c
r
it
e
r
ia
,
w
hi
c
h
m
ig
ht
im
pa
c
t
th
e
qua
nt
it
y
o
f
r
e
s
ul
ts
de
r
iv
e
d
f
r
om
th
e
s
e
le
c
te
d
r
e
s
e
a
r
c
h.
F
ur
th
e
r
m
or
e
,
a
s
c
r
ut
in
y
o
f
th
e
s
tu
di
e
s
w
e
a
na
ly
z
e
d
a
ll
ow
s
u
s
to
di
s
ti
ll
th
e
pr
im
a
r
y
is
s
u
e
s
a
nd
c
on
s
tr
a
in
ts
th
e
y
c
onf
r
ont
.
T
he
s
e
e
nc
om
pa
s
s
a
li
m
it
e
d
da
ta
ba
s
e
,
s
tr
uc
tu
r
a
l
a
s
pe
c
ts
of
r
e
s
e
a
r
c
h,
s
c
a
l
a
bi
li
ty
is
s
ue
s
f
or
r
e
a
l
-
ti
m
e
a
na
ly
s
is
w
it
h
e
xt
e
ns
iv
e
w
e
b
pa
g
e
vol
um
e
s
,
pr
e
c
is
io
n
in
de
te
c
ti
ng
a
bbr
e
vi
a
ti
ons
,
a
nd
th
e
te
xt
ua
l
le
ngt
h
of
m
e
s
s
a
ge
s
pe
r
e
xpe
r
im
e
nt
.
N
ot
a
bl
y,
th
e
r
e
is
a
de
a
r
th
of
upda
te
d
s
ys
te
m
a
ti
c
r
e
vi
e
w
s
r
e
ga
r
di
ng
th
e
r
e
s
e
a
r
c
h
to
pi
c
s
ur
r
ounding
th
e
us
e
of
c
la
s
s
if
ic
a
ti
on
a
lg
or
it
hm
s
f
or
s
m
is
hi
ng
d
e
te
c
ti
on.
G
iv
e
n
th
a
t
th
i
s
te
c
hnol
ogy
h
a
s
e
m
e
r
ge
d
in
r
e
c
e
nt
ye
a
r
s
,
a
nd
e
xpe
r
im
e
nt
s
in
th
is
dom
a
in
a
r
e
ongoing,
th
e
e
f
f
e
c
ti
ve
n
e
s
s
of
th
e
m
e
th
ods
pr
opos
e
d
in
th
is
s
tu
dy
in
a
r
e
a
l
-
w
or
ld
e
nvi
r
onm
e
nt
r
e
m
a
in
s
a
s
ubj
e
c
t
f
or
f
ur
th
e
r
i
nve
s
ti
ga
ti
on.
4.
C
O
N
C
L
U
S
I
O
N
T
h
i
s
s
t
ud
y
e
s
t
a
b
li
s
h
e
s
a
pr
e
c
i
s
e
a
n
d
c
l
e
a
r
w
o
r
k
in
g
m
e
t
ho
d
ol
o
g
y
f
or
r
e
vi
e
w
i
ng
t
h
e
a
pp
li
c
a
t
io
n
of
c
l
a
s
s
if
i
c
a
ti
on
a
l
gor
it
hm
s
i
n
s
m
i
s
hi
ng
d
e
te
c
ti
on
o
n
m
o
bi
l
e
d
e
vi
c
e
s
.
I
n
t
e
g
r
a
ti
n
g
va
r
i
ou
s
m
e
t
h
od
s
pr
o
po
s
e
d
b
y
d
if
f
e
r
e
n
t
a
ut
ho
r
s
f
or
m
s
a
c
o
m
p
r
e
h
e
n
s
i
v
e
f
r
a
m
e
w
o
r
k
t
h
a
t
e
f
f
e
c
t
i
ve
l
y
a
ddr
e
s
s
e
s
e
m
e
r
gi
n
g
c
a
s
e
s
of
s
m
i
s
h
in
g
,
r
e
f
l
e
c
t
in
g
a
h
e
ig
ht
e
n
e
d
r
e
s
e
a
r
c
h
i
nt
e
r
e
s
t
i
n
th
i
s
a
r
e
a
.
W
it
h
s
m
i
s
h
i
ng
,
pa
r
t
ic
u
la
r
l
y
t
h
e
t
r
a
n
s
m
i
s
s
io
n
o
f
m
a
li
c
i
o
u
s
t
e
xt
m
e
s
s
a
g
e
s
w
it
h
U
R
L
s
,
do
m
i
n
a
t
in
g
44
%
o
f
t
h
e
r
e
v
i
e
w
e
d
a
r
ti
c
le
s
,
t
h
e
s
t
ud
y
hi
gh
li
gh
t
s
t
h
e
ur
ge
n
t
n
e
e
d
t
o
t
a
c
kl
e
c
h
a
ll
e
ng
e
s
a
s
s
oc
i
a
t
e
d
w
it
h
t
hi
s
pr
e
v
a
l
e
n
t
p
h
i
s
h
in
g
a
t
ta
c
k
.
D
e
s
pi
t
e
c
o
nt
e
nt
li
m
i
ta
ti
o
n
s
,
th
e
r
e
s
ul
t
s
d
e
m
o
n
s
t
r
a
t
e
c
o
m
m
e
nd
a
bl
e
ou
t
c
o
m
e
s
,
w
i
th
c
o
n
s
i
s
t
e
n
tl
y
h
ig
h
a
c
c
ur
a
c
y
l
e
ve
l
s
s
ur
pa
s
s
i
ng
90%
,
a
v
e
r
a
gi
n
g
a
n
im
pr
e
s
s
iv
e
9
5
.4
8%
.
T
hi
s
u
nd
e
r
s
c
or
e
s
th
e
r
o
b
u
s
t
p
e
r
f
or
m
a
n
c
e
of
a
l
g
or
i
th
m
s
e
m
pl
oy
e
d
i
n
d
e
t
e
c
t
in
g
s
m
i
s
hi
n
g
,
m
a
k
in
g
c
l
a
s
s
if
i
c
a
ti
on
a
lg
or
it
hm
s
p
iv
ot
a
l
i
n
a
s
s
e
s
s
i
ng
e
f
f
e
c
ti
v
e
n
e
s
s
on
m
ob
il
e
d
e
v
i
c
e
s
.
A
c
c
or
d
in
gl
y,
m
o
s
t
s
tu
di
e
s
e
m
pl
o
ye
d
s
t
a
n
da
r
d
c
l
a
s
s
if
ic
a
ti
on
a
lg
or
it
hm
s
,
s
u
c
h
a
s
l
og
i
s
t
i
c
r
e
g
r
e
s
s
i
on
,
K
N
N
,
B
a
y
e
s
N
e
t,
n
a
i
v
e
B
a
y
e
s
,
r
a
di
a
l
b
a
s
i
s
f
un
c
t
i
on
,
d
e
c
i
s
io
n
tr
e
e
,
S
V
M
,
r
a
n
d
om
f
or
e
s
t
,
a
n
d
a
l
s
o
u
s
e
d
d
e
e
p
n
e
ur
a
l
n
e
t
w
o
r
k
s
,
t
o
a
n
a
l
y
z
e
th
e
s
p
e
c
i
f
i
c
c
h
a
r
a
c
t
e
r
i
s
ti
c
s
of
m
a
li
c
i
o
u
s
S
M
S
a
nd
U
R
L
s
.
T
h
e
s
e
t
e
c
hn
iq
u
e
s
pr
ov
e
d
e
f
f
e
c
t
iv
e
,
y
i
e
l
di
ng
pr
om
i
s
i
ng
r
e
s
u
lt
s
w
i
th
h
i
gh
r
a
t
e
s
o
f
tr
u
e
p
o
s
it
iv
e
s
a
n
d
ne
g
a
t
iv
e
s
.
H
ow
e
v
e
r
,
it
i
s
c
r
u
c
i
a
l
to
hi
gh
li
g
ht
a
r
e
a
s
f
or
im
pr
o
ve
m
e
n
t
a
nd
p
r
o
p
o
s
e
a
v
e
nu
e
s
f
or
f
u
tu
r
e
r
e
s
e
a
r
c
h,
in
c
lu
di
n
g
i
nt
e
gr
a
t
in
g
e
n
s
e
m
b
le
l
e
a
r
n
in
g
te
c
hn
i
qu
e
s
,
i
nv
e
s
ti
g
a
ti
n
g
a
lt
e
r
n
a
t
i
ve
no
v
e
l
ty
d
e
t
e
c
t
io
n m
od
e
l
s
,
p
e
r
f
o
r
m
in
g
i
n
-
d
e
pt
h
a
n
a
l
y
s
i
s
of
U
R
L
s
a
nd
S
M
S
m
e
s
s
a
g
e
a
tt
a
c
h
m
e
n
t
s
, a
nd
c
o
n
s
t
a
nt
l
y up
d
a
t
in
g
d
a
t
a
b
a
s
e
s
ho
s
ti
ng
r
e
c
og
n
iz
e
d
p
hi
s
h
in
g
s
i
te
s
to
in
c
r
e
a
s
e
a
c
c
ur
a
c
y
r
a
t
e
s
a
nd
s
tr
e
n
g
th
e
n
t
he
r
e
s
il
i
e
n
c
e
o
f
p
hi
s
hi
n
g
a
n
d
s
m
i
s
h
in
g
d
e
t
e
c
t
io
n
s
y
s
te
m
s
. I
n
c
on
c
lu
s
io
n
, t
h
e
a
n
a
l
y
s
i
s
o
f
ph
is
h
i
ng
d
e
t
e
c
ti
o
n
on
m
ob
il
e
d
e
vi
c
e
s
s
ho
w
s
u
s
a
n
d
p
r
o
v
id
e
s
a
pr
o
m
i
s
in
g
a
ppr
o
a
c
h
b
a
s
e
d
on
m
a
c
h
in
e
l
e
a
r
ni
ng
a
n
d
d
e
e
p
l
e
a
r
n
in
g
t
e
c
h
ni
qu
e
s
.
H
ow
e
v
e
r
,
c
o
nt
in
u
e
d
r
e
s
e
a
r
c
h
i
s
r
e
q
ui
r
e
d
d
u
e
to
t
h
e
i
nc
r
e
a
s
e
of
pr
o
c
e
s
s
e
s
a
nd
a
c
t
iv
it
ie
s
t
ha
t
u
s
e
r
s
c
a
n
pe
r
f
or
m
w
i
th
t
h
e
i
r
c
e
l
l
p
ho
n
e
s
a
n
d
th
e
im
pl
e
m
e
n
ta
ti
o
n
o
f
t
h
e
r
e
c
o
m
m
e
nd
a
ti
on
s
pr
o
po
s
e
d
b
y
th
e
a
u
th
or
s
t
o
f
ur
t
h
e
r
im
pr
ov
e
th
e
d
e
t
e
c
t
io
n
a
nd
m
it
i
ga
ti
o
n
of
t
h
e
s
e
th
r
e
a
t
s
in
t
h
e
f
u
tu
r
e
a
nd
t
h
a
t
t
h
e
pr
op
o
s
e
d
m
e
th
o
do
lo
g
ie
s
do
n
o
t
b
e
c
o
m
e
ou
td
a
te
d
.
A
C
K
N
O
WL
E
D
G
M
E
N
T
S
We
e
x
p
r
e
s
s
t
h
e
s
i
n
c
e
r
e
ly
g
r
a
t
i
t
u
d
e
t
o
T
e
c
h
n
o
l
o
g
i
c
a
l
U
n
i
v
e
r
s
i
t
y
o
f
P
e
r
u
f
o
r
i
t
s
c
o
n
s
t
a
n
t
s
u
p
p
o
r
t
i
n
p
r
o
v
i
d
i
n
g
m
e
w
i
t
h
a
l
l
t
h
e
t
o
o
l
s
a
n
d
i
n
f
r
a
s
t
r
u
c
t
u
r
e
n
e
c
e
s
s
a
r
y
t
o
c
a
r
r
y
o
u
t
t
h
i
s
r
e
s
e
a
r
c
h
,
s
u
c
h
a
s
t
h
e
a
v
a
i
l
a
b
i
l
i
t
y
o
f
l
i
t
e
r
a
t
u
r
e
,
a
c
c
e
s
s
t
o
l
a
b
o
r
a
t
o
r
i
e
s
,
a
n
d
m
a
n
a
g
e
m
e
n
t
s
u
p
p
o
r
t
,
w
h
i
c
h
h
a
v
e
b
e
e
n
f
u
n
d
a
m
e
n
t
a
l
f
o
r
t
h
e
s
u
c
c
e
s
s
o
f
t
h
i
s
p
r
o
j
e
c
t
.
R
E
F
E
R
E
N
C
E
S
[
1]
A
.
A
l
t
huni
ba
t
,
M
.
A
.
A
l
m
a
i
a
h,
a
nd
F
.
A
l
t
a
r
a
w
ne
h,
“
E
xa
m
i
ni
ng
t
he
f
a
c
t
or
s
i
nf
l
ue
nc
i
ng
t
he
m
obi
l
e
l
e
a
r
ni
ng
a
ppl
i
c
a
t
i
ons
us
a
ge
i
n
hi
ghe
r
e
duc
a
t
i
on dur
i
ng t
he
c
ovi
d
-
19 pa
nde
m
i
c
,”
E
l
e
c
t
r
oni
c
s
, vol
. 10, no. 21, 2
021, doi
:
10.3390/
e
l
e
c
t
r
oni
c
s
10212676.
[
2]
G
.
R
.
D.
L
a
z
a
r
o
a
nd
J
.
M
.
D
ua
r
t
,
“
M
ov
i
ng
l
e
a
r
ni
n
g:
a
s
ys
t
e
m
a
t
i
c
r
e
vi
e
w
of
m
ob
i
l
e
l
e
a
r
ni
ng
a
p
pl
i
c
a
t
i
ons
f
or
on
l
i
ne
hi
ghe
r
e
duc
a
t
i
on
,”
J
our
na
l
of
N
e
w
A
p
pr
oac
he
s
i
n
E
d
uc
at
i
onal
R
e
s
e
ar
c
h
,
vol
.
12,
no. 2
,
pp. 198
–
224,
2023
, do
i
:
10
.7821
/
na
e
r
.2023
.7.12
87.
[
3]
M
.
W
.
-
F
e
r
na
ndo,
“
T
he
us
e
of
m
obi
l
e
t
e
c
hnol
ogi
e
s
i
n
onl
i
ne
s
hoppi
ng
dur
i
ng
t
h
e
c
ovi
d
-
19
pa
nde
m
i
c
-
a
n
e
m
pi
r
i
c
a
l
s
t
udy,
”
P
r
oc
e
di
a C
om
put
e
r
S
c
i
e
nc
e
, vol
. 192, pp. 3413
–
3422, 2021, doi
:
10.1016/
j
.pr
oc
s
.2021.09.114.
[
4]
M
.
H
i
j
j
i
a
n
d
G
.
A
l
a
m
,
“
A
m
u
l
t
i
v
oc
a
l
l
i
t
e
r
a
t
u
r
e
r
e
v
i
e
w
on g
r
ow
i
n
g
s
oc
i
a
l
e
n
gi
n
e
e
r
i
ng ba
s
e
d c
yb
e
r
-
a
t
t
a
c
ks
/
t
h
r
e
a
t
s
du
r
i
ng t
he
c
ov
i
d
-
1
9
pa
nd
e
m
i
c
:
c
h
a
l
l
e
n
ge
s
a
nd
p
r
os
p
e
c
t
i
ve
s
o
l
u
t
i
o
ns
,”
I
E
E
E
A
c
c
e
s
s
,
vo
l
.
9
, p
p.
71
52
–
7
169
, 2
02
1,
do
i
:
10
.1
109
/
A
C
C
E
S
S
.2
020
.3
048
83
9.
[
5]
A
.
A
l
z
a
hr
a
ni
,
“
C
or
ona
vi
r
us
s
oc
i
a
l
e
ngi
ne
e
r
i
ng
a
t
t
a
c
k
s
:
I
s
s
ue
s
a
nd
r
e
c
om
m
e
nda
t
i
ons
,”
I
nt
e
r
nat
i
onal
J
ou
r
nal
of
A
dv
anc
e
d
C
om
put
e
r
Sc
i
e
n
c
e
and A
ppl
i
c
at
i
ons
, vol
. 11, no. 5, pp. 154
–
161, 2020, doi
:
10.14569/
I
J
A
C
S
A
.2020.0110523.
[
6]
J
.
Z
hu
a
nd
M
.
W
a
ng,
“
A
na
l
yz
i
ng
t
he
e
f
f
e
c
t
of
pe
opl
e
ut
i
l
i
z
i
ng
m
obi
l
e
t
e
c
hn
ol
ogy
t
o
m
a
ke
b
a
nki
ng
s
e
r
vi
c
e
s
m
or
e
a
c
c
e
s
s
i
bl
e
,
”
F
r
ont
i
e
r
s
i
n P
ubl
i
c
H
e
al
t
h
, vol
. 10, 2022, doi
:
10.3389/
f
pubh.2022.879342.
[
7]
H
.
A
.
M
.
W
a
hs
he
h
a
nd
M
.
S
.
A
l
-
Z
a
hr
a
ni
,
“
L
i
ght
w
e
i
ght
c
r
ypt
ogr
a
phi
c
a
nd
a
r
t
i
f
i
c
i
a
l
i
nt
e
l
l
i
ge
nc
e
m
ode
l
s
f
or
a
nt
i
-
S
m
i
s
hi
ng
,”
L
e
c
t
ur
e
N
ot
e
s
i
n N
e
t
w
o
r
k
s
and S
y
s
t
e
m
s
, vol
. 322, pp. 483
–
496, 2022, doi
:
10.1007/
978
-
3
-
030
-
85990
-
9_39.
[
8]
S
.
A
bdi
,
I
.
K
i
t
s
a
r
a
,
M
.
S
.
H
a
w
l
e
y,
a
nd
L
.
P
.
de
W
i
t
t
e
,
“
E
m
e
r
gi
ng
t
e
c
hnol
ogi
e
s
a
nd
t
he
i
r
pot
e
nt
i
a
l
f
or
ge
ne
r
a
t
i
ng
ne
w
a
s
s
i
s
t
i
v
e
t
e
c
hnol
ogi
e
s
,”
A
s
s
i
s
t
i
v
e
T
e
c
hnol
ogy
, vol
. 33, pp. 17
–
26, 2021, doi
:
10.1080/
10
400435.2021.1945704.
[
9]
K
.
G
a
i
,
Y
.
W
u,
L
.
Z
hu,
Z
.
Z
ha
ng,
a
nd
M
.
Q
i
u,
“
D
i
f
f
e
r
e
nt
i
a
l
p
r
i
va
c
y
-
ba
s
e
d
bl
oc
kc
ha
i
n
f
or
i
ndus
t
r
i
a
l
i
nt
e
r
ne
t
-
of
-
t
hi
ngs
,”
I
E
E
E
T
r
ans
ac
t
i
ons
on I
ndus
t
r
i
al
I
nf
or
m
at
i
c
s
, vol
. 16, no. 6, pp. 4156
–
4165, 2020, do
i
:
10.1109/
T
I
I
.2019.2948094.
[
10]
P
.
D
.
A
m
e
ya
w
a
nd
W
.
T
.
D.
V
r
i
e
s
,
“
B
l
oc
kc
ha
i
n
t
e
c
hnol
ogy
a
da
pt
a
t
i
on
f
or
l
a
n
d
a
dm
i
ni
s
t
r
a
t
i
on
s
e
r
vi
c
e
s
:
T
he
i
m
por
t
a
nc
e
of
s
oc
i
o
-
c
ul
t
ur
a
l
e
l
e
m
e
nt
s
,”
L
and U
s
e
P
ol
i
c
y
, vol
. 125, 2023, doi
:
10.1016/
j
.l
a
ndus
e
pol
.
2022.106485.
[
11]
M
.
I
r
a
nm
a
ne
s
h,
P
.
M
a
r
ouf
kha
ni
,
S
.
A
s
a
di
,
M
.
G
hoba
khl
oo,
Y
.
K
.
D
w
i
ve
di
,
a
nd
M
.
L
.
T
s
e
ng,
“
E
f
f
e
c
t
s
of
s
uppl
y
c
ha
i
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
A
r
ti
f
I
nt
e
ll
I
S
S
N
:
2252
-
8938
A
ppl
ic
at
io
n of
c
la
s
s
if
ic
at
io
n al
gor
it
hm
s
f
or
s
m
i
s
hi
ng de
te
c
ti
on
on m
obi
le
…
(
D
y
la
n F
ar
e
dh C
al
e
r
o Si
nc
he
)
3759
t
r
a
ns
pa
r
e
nc
y,
a
l
i
gnm
e
nt
,
a
da
pt
a
bi
l
i
t
y,
a
nd
a
gi
l
i
t
y
on
bl
oc
kc
ha
i
n
a
dopt
i
on
i
n
s
uppl
y
c
ha
i
n
a
m
ong
S
M
E
s
,”
C
o
m
put
e
r
s
and
I
ndus
t
r
i
al
E
ngi
ne
e
r
i
ng
, vol
. 176, 2023, doi
:
10.1016/
j
.c
i
e
.2022.108931.
[
12]
M
.
O
.
M
o
m
o
h
,
P
.
U
.
C
h
i
ne
d
u
,
W
.
N
w
a
n
kw
o
,
D
.
A
l
i
u,
a
n
d
M
.
S
.
S
ha
b
a
,
“
B
l
oc
k
c
ha
i
n
a
do
p
t
i
o
n
:
a
p
p
l
i
c
a
t
i
o
ns
a
n
d
c
ha
l
l
e
n
g
e
s
,
”
I
n
t
e
r
na
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
S
o
f
t
w
ar
e
E
n
g
i
n
e
e
r
i
ng
a
n
d
C
om
p
u
t
e
r
S
y
s
t
e
m
s
,
v
o
l
.
7
,
n
o.
2
,
p
p
.
19
–
2
5
,
2
02
1
,
d
o
i
:
1
0
.
15
2
8
2
/
i
j
s
e
c
s
.
7
.
2.
2
0
2
1.
3
.
0
08
6
.
[
13]
P
.
J
i
a
ng
e
t
al
.
,
“
B
l
oc
kc
ha
i
n
t
e
c
hnol
ogy
a
ppl
i
c
a
t
i
ons
i
n
w
a
s
t
e
m
a
na
g
e
m
e
nt
:
O
ve
r
vi
e
w
,
c
ha
l
l
e
nge
s
a
nd
oppor
t
uni
t
i
e
s
,”
J
our
nal
o
f
C
l
e
ane
r
P
r
oduc
t
i
on
, vol
. 421, 2023, doi
:
10.1016/
j
.j
c
l
e
pr
o.2023.138466.
[
14]
N
.
S
hohr
uhxon,
“
L
e
v
e
r
a
gi
ng
bl
oc
kc
ha
i
n
t
e
c
hnol
ogy
i
n
s
m
a
l
l
bu
s
i
ne
s
s
e
s
:
e
x
pl
or
i
ng
t
he
pr
os
a
nd
c
ons
,”
U
ni
v
e
r
s
al
J
our
nal
of
A
c
ade
m
i
c
and M
ul
t
i
di
s
c
i
pl
i
nar
y
R
e
s
e
ar
c
h
, vol
. 1, no. 2, pp. 63
–
67
.
[
15]
M
.
A
l
i
m
oha
m
m
a
dl
ou
a
nd
S
.
A
l
i
ne
j
a
d,
“
C
h
a
l
l
e
nge
s
of
bl
oc
kc
h
a
i
n
i
m
pl
e
m
e
nt
a
t
i
on
i
n
S
M
E
s
’
s
uppl
y
c
ha
i
ns
:
a
n
i
nt
e
gr
a
t
e
d
I
T
2F
-
B
W
M
a
nd I
T
2F
-
D
E
M
A
T
E
L
m
e
t
hod,”
E
l
e
c
t
r
oni
c
C
om
m
e
r
c
e
R
e
s
e
a
r
c
h
, 2016, p
p. 1
–
6, 2023, doi
:
10.1007/
s
10660
-
023
-
09696
-
3.
[
16]
J
. L
e
e
, Y
.
L
e
e
, D
.
L
e
e
,
H
. K
w
on, a
nd
D
. S
hi
n, “
C
l
a
s
s
i
f
i
c
a
t
i
on of
a
t
t
a
c
k t
ype
s
a
nd a
na
l
ys
i
s
of
a
t
t
a
c
k m
e
t
hods
f
or
pr
of
i
l
i
ng ph
i
s
hi
ng
m
a
i
l
a
t
t
a
c
k gr
oups
,”
I
E
E
E
A
c
c
e
s
s
, vol
. 9, pp. 80866
–
80872, 2021, doi
:
10.1109
/
A
C
C
E
S
S
.2021.3084897.
[
17]
C
.
P
a
t
s
a
ki
s
,
F
.
C
a
s
i
no,
N
.
L
ykous
a
s
,
a
nd
V
.
K
a
t
os
,
“
U
nr
a
ve
l
l
i
ng
A
r
i
a
dne
’
s
t
h
r
e
a
d:
e
xpl
or
i
ng
t
he
t
hr
e
a
t
s
of
de
c
e
nt
r
a
l
i
s
e
d
D
N
S
,
”
I
E
E
E
A
c
c
e
s
s
, vol
. 8, pp. 118559
–
118571, 2020, doi
:
10.1109/
A
C
C
E
S
S
.2020.3004727.
[
18]
R
.
N
.
K
a
r
t
hi
ka
,
C
.
V
a
l
l
i
ya
m
m
a
i
,
a
nd
M
.
N
a
ve
e
na
,
“
P
hi
s
h
bl
oc
k:
a
bl
oc
kc
ha
i
n
f
r
a
m
e
w
or
k
f
or
phi
s
h
de
t
e
c
t
i
on
i
n
c
l
oud,”
C
om
put
e
r
Sy
s
t
e
m
s
S
c
i
e
nc
e
and E
ngi
ne
e
r
i
ng
, vol
. 44, no. 1, pp. 777
–
795, 2022, doi
:
10.32
604/
c
s
s
e
.2023.024086.
[
19]
S
.
C
ha
nt
i
a
nd
T
.
C
hi
t
hr
a
l
e
kha
,
“
A
l
i
t
e
r
a
t
ur
e
r
e
vi
e
w
on
c
l
a
s
s
i
f
i
c
a
t
i
on
of
phi
s
hi
ng
a
t
t
a
c
ks
,”
I
nt
e
r
nat
i
onal
J
our
nal
of
A
dv
anc
e
d
T
e
c
hnol
ogy
and E
ngi
ne
e
r
i
ng E
x
pl
or
at
i
on
, vol
. 9, no. 89, pp. 446
–
476, 2022, doi
:
10.19101/
I
J
A
T
E
E
.2021.875031.
[
20]
M
.
J
.
P
a
ge
e
t
al
.
,
“
P
R
I
S
M
A
2020
e
xpl
a
na
t
i
on
a
nd
e
l
a
bor
a
t
i
on:
U
pda
t
e
d
gui
da
nc
e
a
nd
e
xe
m
pl
a
r
s
f
or
r
e
por
t
i
ng
s
ys
t
e
m
a
t
i
c
r
e
vi
e
w
s
,”
T
he
B
M
J
, vol
. 372, 2021, doi
:
10.1136/
bm
j
.n160.
[
21]
M
.
J
.
P
a
ge
e
t
al
.
,
“
T
he
P
R
I
S
M
A
2020
s
t
a
t
e
m
e
nt
:
A
n
upda
t
e
d
gui
de
l
i
ne
f
or
r
e
por
t
i
ng
s
ys
t
e
m
a
t
i
c
r
e
vi
e
w
s
,”
T
he
B
M
J
,
vol
.
372,
2021, doi
:
10.1136/
bm
j
.n71.
[
22]
G
.
R
obl
e
da
,
“
S
t
r
uc
t
ur
e
d
que
s
t
i
on
t
o
ge
ne
r
a
t
e
s
e
a
r
c
h
f
or
a
s
ys
t
e
m
a
t
i
c
r
e
vi
e
w
,”
E
nf
e
r
m
e
r
í
a
I
nt
e
ns
i
v
a
,
vol
.
30,
no.
3,
pp.
144
–
147,
2019, doi
:
10.1016/
j
.e
nf
i
e
.2019.07.001.
[
23]
U
.
I
.
A
kpa
n
a
nd
A
.
S
t
a
r
ke
y,
“
R
e
vi
e
w
of
c
l
a
s
s
i
f
i
c
a
t
i
on
a
l
gor
i
t
hm
s
w
i
t
h
c
ha
ng
i
ng
i
nt
e
r
-
c
l
a
s
s
di
s
t
a
n
c
e
s
,”
M
ac
hi
ne
L
e
ar
ni
ng
w
i
t
h
A
ppl
i
c
at
i
ons
, vol
. 4, 2021, doi
:
10.1016/
j
.m
l
w
a
.2021.100031.
[
24]
K
.
H
a
yne
s
,
H
.
S
hi
r
a
z
i
,
a
nd
I
.
R
a
y,
“
L
i
ght
w
e
i
ght
U
R
L
-
ba
s
e
d
phi
s
hi
ng
de
t
e
c
t
i
on
us
i
ng
na
t
ur
a
l
l
a
ngua
ge
pr
oc
e
s
s
i
ng
t
r
a
ns
f
or
m
e
r
s
f
or
m
obi
l
e
de
vi
c
e
s
,”
P
r
oc
e
di
a C
om
put
e
r
Sc
i
e
nc
e
, vol
. 191, pp. 127
–
134, 2021,
doi
:
10.1016/
j
.pr
oc
s
.2021.07.040.
[
25]
A
.
K
.
J
a
i
n,
N
.
D
e
bna
t
h,
a
nd
A
.
K
.
J
a
i
n,
“
A
P
uM
L
:
A
n
e
f
f
i
c
i
e
nt
a
ppr
oa
c
h
t
o
de
t
e
c
t
m
obi
l
e
phi
s
hi
ng
w
e
bpa
ge
s
us
i
ng
m
a
c
hi
ne
l
e
a
r
ni
ng,”
W
i
r
e
l
e
s
s
P
e
r
s
onal
C
om
m
uni
c
at
i
on
s
, vol
. 125, no. 4, pp. 3227
–
3248,
2022, doi
:
10.1007/
s
11277
-
022
-
09707
-
w.
[
26]
S
.
M
a
hda
vi
f
a
r
a
nd
A
.
A
.
G
hor
ba
ni
,
“
D
e
N
N
e
S
:
de
e
p
e
m
be
dde
d
ne
ur
a
l
ne
t
w
or
k
e
xpe
r
t
s
ys
t
e
m
f
or
de
t
e
c
t
i
ng
c
ybe
r
a
t
t
a
c
ks
,”
N
e
ur
a
l
C
om
put
i
ng and A
ppl
i
c
at
i
ons
, vol
. 32, no. 18, pp. 14753
–
14780, 2020, doi
:
10.1007/
s
00521
-
020
-
04830
-
w.
[
27]
M
.
Z
oui
na
a
nd
B
.
O
ut
t
a
j
,
“
A
nove
l
l
i
ght
w
e
i
ght
U
R
L
phi
s
hi
ng
de
t
e
c
t
i
on
s
ys
t
e
m
us
i
ng
S
V
M
a
nd
s
i
m
i
l
a
r
i
t
y
i
nde
x,”
H
um
an
-
C
e
nt
r
i
c
C
om
put
i
ng and I
nf
or
m
at
i
on Sc
i
e
nc
e
s
, vol
. 7, no. 1, 2017, doi
:
10.1186/
s
13673
-
017
-
0098
-
1.
[
28]
S
.
K
.
Z
a
w
a
nd
S
.
V
a
s
uponga
yya
,
“
E
nha
nc
i
ng
c
a
s
e
-
ba
s
e
d
r
e
a
s
oni
ng
a
ppr
oa
c
h
us
i
ng
i
nc
r
e
m
e
nt
a
l
l
e
a
r
ni
ng
m
ode
l
f
o
r
a
ut
om
a
t
i
c
a
da
pt
a
t
i
on of
c
l
a
s
s
i
f
i
e
r
s
i
n m
obi
l
e
phi
s
hi
ng d
e
t
e
c
t
i
on,”
I
nt
e
r
nat
i
onal
J
our
nal
of
N
e
t
w
or
k
e
d and
D
i
s
t
r
i
but
e
d
C
om
put
i
ng
, vol
. 8, no
.
3, pp. 152
–
161, 2020, doi
:
10.2991/
i
j
ndc
.k.200515.001.
[
29]
A
.
G
hour
a
bi
,
M
.
A
.
M
a
hm
ood,
a
nd
Q
.
M
.
A
l
z
ubi
,
“
A
hybr
i
d
C
N
N
-
L
S
T
M
m
ode
l
f
or
S
M
S
s
pa
m
de
t
e
c
t
i
on
i
n
a
r
a
bi
c
a
nd
e
ngl
i
s
h
m
e
s
s
a
ge
s
,”
F
ut
ur
e
I
nt
e
r
n
e
t
, vol
. 12, no. 9, 2020, doi
:
10.3390/
F
I
12090156.
[
30]
S
.
M
i
s
hr
a
a
nd
D
.
S
oni
,
“
D
S
m
i
s
hS
M
S
-
A
s
ys
t
e
m
t
o
de
t
e
c
t
s
m
i
s
hi
ng
S
M
S
,”
N
e
ur
al
C
om
put
i
ng
and
A
ppl
i
c
at
i
ons
,
vol
.
35,
no.
7,
pp.
4975
–
4992, 2023, doi
:
10.1007/
s
00521
-
021
-
06305
-
y.
[
31]
R
.
E
.
U
l
f
a
t
h,
H
.
A
l
qa
ht
a
ni
,
M
.
H
a
m
m
oude
h,
a
nd
I
.
H
.
S
a
r
ke
r
,
“
H
ybr
i
d
C
N
N
-
G
R
U
f
r
a
m
e
w
or
k
w
i
t
h
i
nt
e
gr
a
t
e
d
pr
e
-
t
r
a
i
ne
d
l
a
ngua
ge
t
r
a
ns
f
or
m
e
r
f
or
S
M
S
phi
s
hi
ng
de
t
e
c
t
i
on,”
A
C
M
I
nt
e
r
nat
i
onal
C
onf
e
r
e
nc
e
P
r
oc
e
e
di
ng
Se
r
i
e
s
,
pp.
244
–
251,
2021,
doi
:
10.1145/
3508072.3508109.
[
32]
M
. K
or
km
a
z
, O
. K
. S
a
hi
ngo
z
, a
nd
B
. D
i
r
i
, “
D
e
t
e
c
t
i
on of
phi
s
hi
ng
w
e
bs
i
t
e
s
by
us
i
ng m
a
c
hi
ne
l
e
a
r
ni
ng
-
ba
s
e
d
U
R
L
a
na
l
y
s
i
s
,”
202
0
11t
h
I
nt
e
r
nat
i
onal
C
onf
e
r
e
nc
e
on
C
om
put
i
ng,
C
om
m
uni
c
at
i
on
and
N
e
t
w
or
k
i
ng
T
e
c
hnol
ogi
e
s
,
pp.
1
-
7,
2020,
doi
:
10.1109/
I
C
C
C
N
T
49239.2020.9225561.
[
33]
S
.
M
i
s
hr
a
a
nd
D
.
S
oni
,
“
S
m
i
s
hi
ng
de
t
e
c
t
or
:
a
s
e
c
ur
i
t
y
m
ode
l
t
o
de
t
e
c
t
S
m
i
s
hi
n
g
t
hr
ough
S
M
S
c
ont
e
nt
a
na
l
ys
i
s
a
nd
U
R
L
be
ha
vi
or
a
na
l
ys
i
s
,”
F
ut
ur
e
G
e
ne
r
at
i
on C
o
m
put
e
r
Sy
s
t
e
m
s
, vol
. 108, pp. 803
–
815, 2020,
doi
:
10.1016/
j
.f
ut
ur
e
.2020.03.021.
[
34]
A
.
R
.
M
a
hm
ood
a
nd
S
.
M
.
H
a
m
e
e
d,
“
R
e
vi
e
w
of
s
m
i
s
hi
ng
d
e
t
e
c
t
i
on
vi
a
m
a
c
hi
ne
l
e
a
r
ni
ng,”
I
r
aqi
J
our
nal
of
Sc
i
e
nc
e
,
vol
.
64,
no.
8, pp. 4244
–
4259, 2023, doi
:
10.24996/
i
j
s
.2023.64.8.42.
[
35]
I
I
S
E
C
,
A
.
V
a
r
ol
,
a
nd
I
E
E
E
,
“
I
nnova
t
i
ve
t
e
c
hnol
ogi
e
s
f
or
di
g
i
t
a
l
t
r
a
ns
f
or
m
a
t
i
on,”
1s
t
I
nt
e
r
nat
i
onal
I
nf
or
m
at
i
c
s
and
Sof
t
w
ar
e
E
ngi
ne
e
r
i
ng C
onf
e
r
e
nc
e
(
I
I
SE
C
-
2019)
,
2019.
[
36]
I
.
S
.
M
a
m
bi
na
,
J
.
D
.
N
di
bw
i
l
e
,
a
nd
K
.
F
.
M
i
c
ha
e
l
,
“
C
l
a
s
s
i
f
yi
ng
s
w
a
hi
l
i
S
m
i
s
hi
ng
a
t
t
a
c
ks
f
or
m
obi
l
e
m
one
y
us
e
r
s
:
a
m
a
c
hi
ne
-
l
e
a
r
ni
ng a
ppr
oa
c
h,”
I
E
E
E
A
c
c
e
s
s
, vol
. 10, pp. 83061
–
83074, 2022, doi
:
10.1109/
A
C
C
E
S
S
.2022.3196464.
[
37]
G
.
G
i
or
gi
,
A
.
S
a
r
a
c
i
no,
a
nd
F
.
M
a
r
t
i
ne
l
l
i
,
“
E
m
a
i
l
s
poof
i
ng
a
t
t
a
c
k
d
e
t
e
c
t
i
on
t
hr
ough
a
n
e
nd
-
to
-
e
nd
a
ut
hor
s
hi
p
a
t
t
r
i
but
i
on
s
ys
t
e
m
,
”
I
nt
e
r
nat
i
onal
C
onf
e
r
e
nc
e
on I
nf
or
m
at
i
on Sy
s
t
e
m
s
Se
c
ur
i
t
y
and P
r
i
v
ac
y
, pp. 64
–
74, 2020, doi
:
10.5220/
0008954600640074.
[
38]
B
.
L
.
J
.
C
hua
n,
M
.
M
.
S
i
n
gh,
a
n
d
A
.
R
.
M
.
S
ha
r
i
f
f
,
“
A
P
T
G
ua
r
d
:
A
dv
a
nc
e
d
pe
r
s
i
s
t
e
nt
t
h
r
e
a
t
(
A
P
T
)
d
e
t
e
c
t
i
ons
a
n
d
p
r
e
di
c
t
i
ons
us
i
ng
a
nd
r
o
i
d s
m
a
r
t
ph
one
,”
L
e
c
t
ur
e
N
o
t
e
s
i
n
E
l
e
c
t
r
i
c
al
E
ng
i
ne
e
r
i
n
g
,
vo
l
.
4
81,
p
p.
54
5
–
555
, 2
01
9,
do
i
:
10
.1
007
/
9
78
-
9
81
-
13
-
26
22
-
6
_53
.
[
39]
M
.
R
a
j
a
b,
“
V
i
s
ua
l
i
z
a
t
i
on
m
ode
l
ba
s
e
d
on
phi
s
hi
ng
f
e
a
t
ur
e
s
,”
J
our
nal
of
I
nf
or
m
at
i
on
and
K
now
l
e
dge
M
anage
m
e
nt
,
vol
.
18,
no.
1,
2019, doi
:
10.1142/
S
0219649219500102.
[
40]
R
. B
.
M
. S
hi
va
kum
a
r
,
B
. D
.
P
a
r
a
m
e
s
ha
c
h
a
r
i
, “
G
S
S
S
i
ns
t
i
t
ut
e
of
e
ngi
ne
e
r
i
ng a
n
d t
e
c
hnol
ogy f
or
w
om
e
n, i
n
s
t
i
t
ut
e
of
e
l
e
c
t
r
i
c
a
l
a
nd
e
l
e
c
t
r
oni
c
s
e
ngi
ne
e
r
s
.
ba
nga
l
or
e
s
e
c
t
i
on,
a
nd
i
ns
t
i
t
ut
e
of
e
l
e
c
t
r
i
c
a
l
a
nd
e
l
e
c
t
r
oni
c
s
e
ngi
ne
e
r
s
,”
4t
h
I
nt
e
r
nat
i
onal
C
onf
e
r
e
nc
e
o
n
E
l
e
c
t
r
i
c
al
, E
l
e
c
t
r
oni
c
s
, C
om
m
uni
c
at
i
on, C
om
put
e
r
T
e
c
hnol
ogi
e
s
nd O
pt
i
m
i
z
at
i
on T
e
c
hni
que
s
:
I
C
E
E
C
C
O
T
-
2019
, 2018.
[
41]
O
. N
. A
ka
nd
e
e
t
al
.
, “
S
M
S
P
R
O
T
E
C
T
:
A
n
a
ut
om
a
t
i
c
S
m
i
s
hi
ng
d
e
t
e
c
t
i
on m
obi
l
e
a
ppl
i
c
a
t
i
on,”
I
C
T
E
x
pr
e
s
s
, vol
.
9, no.
2, pp.
168
–
176,
2023, doi
:
10.1016/
j
.i
c
t
e
.2022.05.009.
[
42]
D
.
G
oe
l
a
nd
A
.
K
.
J
a
i
n,
“
S
m
i
s
hi
ng
-
c
l
a
s
s
i
f
i
e
r
:
A
nove
l
f
r
a
m
e
w
or
k
f
or
de
t
e
c
t
i
on
of
S
m
i
s
hi
ng
a
t
t
a
c
k
i
n
m
obi
l
e
e
nvi
r
onm
e
nt
,”
C
om
m
uni
c
at
i
ons
i
n C
om
put
e
r
and I
nf
or
m
at
i
on Sc
i
e
nc
e
, vol
. 828, pp. 502
–
512,
2018, doi
:
10.1007/
978
-
981
-
10
-
8660
-
1_38.
[
43]
A
.
K
.
J
a
i
n
a
nd
B
.
B
.
G
upt
a
,
“
R
ul
e
-
ba
s
e
d
f
r
a
m
e
w
or
k
f
or
de
t
e
c
t
i
on
of
S
m
i
s
hi
ng
m
e
s
s
a
ge
s
i
n
m
obi
l
e
e
nvi
r
onm
e
nt
,”
P
r
oc
e
di
a
C
om
put
e
r
Sc
i
e
n
c
e
, vol
. 125, pp. 617
–
623, 2018, doi
:
10.1016/
j
.pr
oc
s
.2017.12.079.
[
44]
G
.
S
onow
a
l
a
nd
K
.
S
.
K
uppus
a
m
y,
“
S
M
I
D
C
A
:
A
n
a
nt
i
-
S
m
i
s
hi
ng
m
ode
l
w
i
t
h
m
a
c
hi
ne
l
e
a
r
ni
ng
a
ppr
oa
c
h,”
C
om
put
e
r
J
ou
r
nal
,
vol
. 61, no. 8, pp. 1143
–
1157, 2018, doi
:
10.1093/
c
om
j
nl
/
bxy039.
[
45]
S
.
Y
.
Y
e
r
i
m
a
a
nd
A
.
B
a
s
ha
r
,
“
S
e
m
i
-
s
upe
r
vi
s
e
d
nove
l
t
y
de
t
e
c
t
i
on
w
i
t
h
one
c
l
a
s
s
S
V
M
f
or
S
M
S
s
pa
m
de
t
e
c
t
i
on,”
I
nt
e
r
nat
i
onal
C
onf
e
r
e
nc
e
on Sy
s
t
e
m
s
, Si
gnal
s
, and I
m
age
P
r
oc
e
s
s
i
ng
, vol
. 2022, 2022, doi
:
1
0.1109/
I
W
S
S
I
P
55020.2022.9854496.
[
46]
A
.
K
.
J
a
i
n,
B
.
B
.
G
upt
a
,
K
.
K
a
ur
,
P
.
B
hut
a
ni
,
W
.
A
l
ha
l
a
bi
,
a
nd
A
.
A
l
m
om
a
ni
,
“
A
c
ont
e
nt
a
nd
U
R
L
a
na
l
ys
i
s
-
ba
s
e
d
e
f
f
i
c
i
e
nt
Evaluation Warning : The document was created with Spire.PDF for Python.